Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 809 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.9207. Min Act: -0.1700
Data Index: 4441769 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.4207. Min Act: -0.1700
Data Index: 4441771 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.3270. Min Act: -0.1700
Data Index: 4441770 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.2957. Min Act: -0.1700
Data Index: 7049553 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.1082. Min Act: -0.1700
Data Index: 6182161 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.0770. Min Act: -0.1700
Data Index: 1381440 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.9832. Min Act: -0.1700
Data Index: 2825308 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.9832. Min Act: -0.1700
Data Index: 1356398 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.9832. Min Act: -0.1700
Data Index: 1505853 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.9520. Min Act: -0.1700
Data Index: 8346355 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8895. Min Act: -0.1700
Data Index: 6664521 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8895. Min Act: -0.1700
Data Index: 6981028 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8270. Min Act: -0.1700
Data Index: 5754564 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8270. Min Act: -0.1700
Data Index: 4088795 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8270. Min Act: -0.1700
Data Index: 3723545 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8270. Min Act: -0.1700
Data Index: 5754565 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8270. Min Act: -0.1700
Data Index: 7179444 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8270. Min Act: -0.1700
Data Index: 526610 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8270. Min Act: -0.1700
Data Index: 8311216 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9207. Min Range: -5.9207
Max Act: 4.8582. Min Act: -0.1700
Data Index: 2300904 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19