Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.1541. Min Act: -0.1700
Data Index: 7931742 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.1229. Min Act: -0.1700
Data Index: 7477313 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.1229. Min Act: -0.1700
Data Index: 4706293 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0916. Min Act: -0.1700
Data Index: 43742 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0916. Min Act: -0.1700
Data Index: 8782930 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0604. Min Act: -0.1700
Data Index: 7751572 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0604. Min Act: -0.1700
Data Index: 8002647 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0604. Min Act: -0.1700
Data Index: 2517162 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0291. Min Act: -0.1700
Data Index: 6048946 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0291. Min Act: -0.1700
Data Index: 5511389 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0291. Min Act: -0.1700
Data Index: 4886929 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0291. Min Act: -0.1700
Data Index: 7333855 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0604. Min Act: -0.1700
Data Index: 494187 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0291. Min Act: -0.1700
Data Index: 196425 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1541. Min Range: -6.1541
Max Act: 6.0291. Min Act: -0.1700
Data Index: 6205619 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1541. Min Range: -6.1541
Max Act: 5.9979. Min Act: -0.1700
Data Index: 3143898 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1541. Min Range: -6.1541
Max Act: 5.9979. Min Act: -0.1700
Data Index: 7281801 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1541. Min Range: -6.1541
Max Act: 5.9979. Min Act: -0.1700
Data Index: 1084345 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1541. Min Range: -6.1541
Max Act: 5.9666. Min Act: -0.1700
Data Index: 4977977 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1541. Min Range: -6.1541
Max Act: 5.9666. Min Act: -0.1700
Data Index: 5401837 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19