Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 924 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.4993. Min Act: -0.1700
Data Index: 2376290 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.4055. Min Act: -0.1700
Data Index: 3004075 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.4055. Min Act: -0.1700
Data Index: 7419609 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.3743. Min Act: -0.1700
Data Index: 511899 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.2805. Min Act: -0.1700
Data Index: 5431913 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.2805. Min Act: -0.1700
Data Index: 4274124 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.2805. Min Act: -0.1700
Data Index: 2420877 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.3118. Min Act: -0.1700
Data Index: 4064090 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.2493. Min Act: -0.1700
Data Index: 854127 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.2805. Min Act: -0.1700
Data Index: 6552618 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.2493. Min Act: -0.1700
Data Index: 1308698 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.2493. Min Act: -0.1700
Data Index: 616842 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.3118. Min Act: -0.1700
Data Index: 4682469 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.2805. Min Act: -0.1700
Data Index: 1943738 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.2493. Min Act: -0.1700
Data Index: 8541689 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.1868. Min Act: -0.1700
Data Index: 5058691 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.1868. Min Act: -0.1700
Data Index: 2407035 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.1555. Min Act: -0.1700
Data Index: 6966040 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.1555. Min Act: -0.1700
Data Index: 3237552 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4993. Min Range: -6.4993
Max Act: 6.1868. Min Act: -0.1700
Data Index: 6817010 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19