Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.9219. Min Act: -0.1700
Data Index: 1512355 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.9219. Min Act: -0.1700
Data Index: 604731 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.7657. Min Act: -0.1700
Data Index: 7670503 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.7344. Min Act: -0.1700
Data Index: 218613 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.7032. Min Act: -0.1700
Data Index: 3089506 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.6719. Min Act: -0.1700
Data Index: 8000412 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.6407. Min Act: -0.1700
Data Index: 8825360 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.5782. Min Act: -0.1700
Data Index: 2078608 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.5782. Min Act: -0.1700
Data Index: 4360820 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.5469. Min Act: -0.1700
Data Index: 2259545 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.5782. Min Act: -0.1700
Data Index: 1437799 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.5469. Min Act: -0.1700
Data Index: 376459 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.4844. Min Act: -0.1700
Data Index: 3406781 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.4844. Min Act: -0.1700
Data Index: 8261548 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.4532. Min Act: -0.1700
Data Index: 2980533 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.4532. Min Act: -0.1700
Data Index: 2103484 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.4219. Min Act: -0.1700
Data Index: 6496915 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.4219. Min Act: -0.1700
Data Index: 3357217 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.4219. Min Act: -0.1700
Data Index: 4523292 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9219. Min Range: -5.9219
Max Act: 5.4219. Min Act: -0.1700
Data Index: 3172675 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19