Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2612 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.9220. Min Act: -0.1700
Data Index: 4988904 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.7970. Min Act: -0.1700
Data Index: 4369989 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.7345. Min Act: -0.1700
Data Index: 2117389 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.6408. Min Act: -0.1700
Data Index: 8135061 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.6095. Min Act: -0.1700
Data Index: 544936 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.6720. Min Act: -0.1700
Data Index: 7080246 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.6408. Min Act: -0.1700
Data Index: 1436581 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.6095. Min Act: -0.1700
Data Index: 1283211 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.5158. Min Act: -0.1700
Data Index: 6907681 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.4845. Min Act: -0.1700
Data Index: 6611620 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.5158. Min Act: -0.1700
Data Index: 1553398 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.5158. Min Act: -0.1700
Data Index: 3042626 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.5470. Min Act: -0.1700
Data Index: 8451466 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.4845. Min Act: -0.1700
Data Index: 6649993 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.4845. Min Act: -0.1700
Data Index: 4628479 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.4845. Min Act: -0.1700
Data Index: 5372083 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.4845. Min Act: -0.1700
Data Index: 1115193 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.4845. Min Act: -0.1700
Data Index: 6981883 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.4533. Min Act: -0.1700
Data Index: 3323354 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9220. Min Range: -6.9220
Max Act: 6.4533. Min Act: -0.1700
Data Index: 3536783 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19