Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3715 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.9051. Min Act: -0.1700
Data Index: 8438058 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.6864. Min Act: -0.1700
Data Index: 8374315 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.5614. Min Act: -0.1700
Data Index: 7058599 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.5614. Min Act: -0.1700
Data Index: 1254483 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4989. Min Act: -0.1700
Data Index: 7538105 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4676. Min Act: -0.1700
Data Index: 2352823 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.4051. Min Act: -0.1700
Data Index: 629435 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3739. Min Act: -0.1700
Data Index: 8410864 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3739. Min Act: -0.1700
Data Index: 7124158 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3739. Min Act: -0.1700
Data Index: 5111484 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3739. Min Act: -0.1700
Data Index: 8125316 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3739. Min Act: -0.1700
Data Index: 6217306 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3739. Min Act: -0.1700
Data Index: 263026 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3426. Min Act: -0.1700
Data Index: 1095077 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3114. Min Act: -0.1700
Data Index: 2473987 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3426. Min Act: -0.1700
Data Index: 4227957 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3426. Min Act: -0.1700
Data Index: 2896140 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.3114. Min Act: -0.1700
Data Index: 3239053 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.2801. Min Act: -0.1700
Data Index: 7903664 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9051. Min Range: -5.9051
Max Act: 5.2801. Min Act: -0.1700
Data Index: 6611305 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19