Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 858 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6923. Min Act: -0.1700
Data Index: 755395 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.7236. Min Act: -0.1700
Data Index: 6187192 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6923. Min Act: -0.1700
Data Index: 8130387 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6610. Min Act: -0.1700
Data Index: 2690026 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6297. Min Act: -0.1700
Data Index: 4219775 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6454. Min Act: -0.1700
Data Index: 7338598 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6454. Min Act: -0.1700
Data Index: 7565317 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6454. Min Act: -0.1700
Data Index: 1772598 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6141. Min Act: -0.1700
Data Index: 4903646 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5984. Min Act: -0.1700
Data Index: 3346248 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6297. Min Act: -0.1700
Data Index: 4128417 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6141. Min Act: -0.1700
Data Index: 3604076 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5984. Min Act: -0.1700
Data Index: 5320926 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5984. Min Act: -0.1700
Data Index: 6935151 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5828. Min Act: -0.1700
Data Index: 1642651 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6141. Min Act: -0.1700
Data Index: 290734 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6141. Min Act: -0.1700
Data Index: 2914689 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5828. Min Act: -0.1700
Data Index: 4684979 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5828. Min Act: -0.1700
Data Index: 6980707 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5828. Min Act: -0.1700
Data Index: 8782769 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19