Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.7802. Min Act: -0.1700
Data Index: 843984 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.6864. Min Act: -0.1700
Data Index: 3206663 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.6864. Min Act: -0.1700
Data Index: 156532 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.6552. Min Act: -0.1700
Data Index: 4594682 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5614. Min Act: -0.1700
Data Index: 8753699 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5927. Min Act: -0.1700
Data Index: 3527972 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5927. Min Act: -0.1700
Data Index: 3871788 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5927. Min Act: -0.1700
Data Index: 6112808 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5614. Min Act: -0.1700
Data Index: 863656 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5614. Min Act: -0.1700
Data Index: 1106792 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5927. Min Act: -0.1700
Data Index: 1580787 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5302. Min Act: -0.1700
Data Index: 5375951 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.4989. Min Act: -0.1700
Data Index: 8337110 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5302. Min Act: -0.1700
Data Index: 1604938 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.4989. Min Act: -0.1700
Data Index: 7161918 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.4677. Min Act: -0.1700
Data Index: 2013932 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.5302. Min Act: -0.1700
Data Index: 1462326 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.4677. Min Act: -0.1700
Data Index: 2802781 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.4677. Min Act: -0.1700
Data Index: 2294331 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7802. Min Range: -5.7802
Max Act: 5.4677. Min Act: -0.1700
Data Index: 3820325 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19