Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4784 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.4485. Min Act: -0.1700
Data Index: 3478835 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.3860. Min Act: -0.1700
Data Index: 792989 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.3860. Min Act: -0.1700
Data Index: 7081285 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.3547. Min Act: -0.1700
Data Index: 333913 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.3235. Min Act: -0.1700
Data Index: 977344 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.2922. Min Act: -0.1700
Data Index: 2364035 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.2922. Min Act: -0.1700
Data Index: 922351 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.2610. Min Act: -0.1700
Data Index: 4993573 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.2610. Min Act: -0.1700
Data Index: 375193 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.2610. Min Act: -0.1700
Data Index: 5765066 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.2297. Min Act: -0.1700
Data Index: 1434096 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.2297. Min Act: -0.1700
Data Index: 8187757 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.1985. Min Act: -0.1700
Data Index: 6073583 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.2297. Min Act: -0.1700
Data Index: 7729268 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.2297. Min Act: -0.1700
Data Index: 660079 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.1985. Min Act: -0.1700
Data Index: 7193643 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.1985. Min Act: -0.1700
Data Index: 3943843 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.1672. Min Act: -0.1700
Data Index: 1160335 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.1360. Min Act: -0.1700
Data Index: 5795975 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4485. Min Range: -7.4485
Max Act: 7.1360. Min Act: -0.1700
Data Index: 6491668 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19