Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.8147. Min Act: -0.1700
Data Index: 5250758 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.7491. Min Act: -0.1700
Data Index: 799084 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6987. Min Act: -0.1700
Data Index: 5237930 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6723. Min Act: -0.1700
Data Index: 2651347 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6430. Min Act: -0.1700
Data Index: 5617592 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6619. Min Act: -0.1700
Data Index: 4854812 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6433. Min Act: -0.1700
Data Index: 1399028 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6158. Min Act: -0.1700
Data Index: 6572522 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6026. Min Act: -0.1700
Data Index: 7689643 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6166. Min Act: -0.1700
Data Index: 4472012 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6352. Min Act: -0.1700
Data Index: 7639567 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6009. Min Act: -0.1700
Data Index: 1133596 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5988. Min Act: -0.1700
Data Index: 7037555 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6069. Min Act: -0.1700
Data Index: 162967 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.6230. Min Act: -0.1700
Data Index: 4904620 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5571. Min Act: -0.1700
Data Index: 959563 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5693. Min Act: -0.1700
Data Index: 2361289 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5532. Min Act: -0.1700
Data Index: 3923311 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5922. Min Act: -0.1700
Data Index: 4029171 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.8147. Min Range: -3.8147
Max Act: 3.5548. Min Act: -0.1700
Data Index: 2195884 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full textTruncated
Full Text #19