Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0613. Min Range: -8.0613
Max Act: 8.0613. Min Act: -0.1700
Data Index: 8295539 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.8113. Min Act: -0.1700
Data Index: 7188467 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.7175. Min Act: -0.1700
Data Index: 95784 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.6238. Min Act: -0.1700
Data Index: 6590466 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.7488. Min Act: -0.1700
Data Index: 8450592 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.7488. Min Act: -0.1700
Data Index: 7902044 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.6863. Min Act: -0.1700
Data Index: 7496336 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.6863. Min Act: -0.1700
Data Index: 434651 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.6550. Min Act: -0.1700
Data Index: 3911732 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.6863. Min Act: -0.1700
Data Index: 7188466 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.6238. Min Act: -0.1700
Data Index: 2341938 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.6238. Min Act: -0.1700
Data Index: 2645048 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.5925. Min Act: -0.1700
Data Index: 7188465 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.5300. Min Act: -0.1700
Data Index: 3714067 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.4988. Min Act: -0.1700
Data Index: 5623640 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.5613. Min Act: -0.1700
Data Index: 4363021 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.4988. Min Act: -0.1700
Data Index: 1701207 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.5300. Min Act: -0.1700
Data Index: 6066770 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.4675. Min Act: -0.1700
Data Index: 8171776 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0613. Min Range: -8.0613
Max Act: 7.4050. Min Act: -0.1700
Data Index: 3141536 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19