Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3977 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.9657. Min Act: -0.1700
Data Index: 2255990 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.9032. Min Act: -0.1700
Data Index: 554595 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.7157. Min Act: -0.1700
Data Index: 4427855 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.4657. Min Act: -0.1700
Data Index: 6556742 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.3407. Min Act: -0.1700
Data Index: 5602409 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.2782. Min Act: -0.1700
Data Index: 2172141 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.2157. Min Act: -0.1700
Data Index: 2510432 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.2782. Min Act: -0.1700
Data Index: 2103689 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.1532. Min Act: -0.1700
Data Index: 8353255 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.0907. Min Act: -0.1700
Data Index: 4356517 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.0282. Min Act: -0.1700
Data Index: 1977377 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.0282. Min Act: -0.1700
Data Index: 4654484 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.0282. Min Act: -0.1700
Data Index: 5327187 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9657. Min Range: -12.9657
Max Act: 12.0282. Min Act: -0.1700
Data Index: 225325 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9657. Min Range: -12.9657
Max Act: 11.9657. Min Act: -0.1700
Data Index: 1522478 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9657. Min Range: -12.9657
Max Act: 11.9657. Min Act: -0.1700
Data Index: 8327035 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9657. Min Range: -12.9657
Max Act: 11.9657. Min Act: -0.1700
Data Index: 5821681 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9657. Min Range: -12.9657
Max Act: 11.8407. Min Act: -0.1700
Data Index: 3186498 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9657. Min Range: -12.9657
Max Act: 11.8407. Min Act: -0.1700
Data Index: 1977378 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9657. Min Range: -12.9657
Max Act: 11.7782. Min Act: -0.1700
Data Index: 5301739 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19