Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3124 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5541. Min Range: -9.5541
Max Act: 9.5541. Min Act: -0.1700
Data Index: 77134 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5541. Min Range: -9.5541
Max Act: 9.4291. Min Act: -0.1700
Data Index: 235469 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5541. Min Range: -9.5541
Max Act: 9.3666. Min Act: -0.1700
Data Index: 732978 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5541. Min Range: -9.5541
Max Act: 9.1166. Min Act: -0.1700
Data Index: 3200780 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5541. Min Range: -9.5541
Max Act: 9.1166. Min Act: -0.1700
Data Index: 2984663 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5541. Min Range: -9.5541
Max Act: 9.0541. Min Act: -0.1700
Data Index: 6996665 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5541. Min Range: -9.5541
Max Act: 9.0541. Min Act: -0.1700
Data Index: 7923386 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.9916. Min Act: -0.1700
Data Index: 7373043 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.9916. Min Act: -0.1700
Data Index: 415620 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.9916. Min Act: -0.1700
Data Index: 3477628 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.9291. Min Act: -0.1700
Data Index: 7041095 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.8666. Min Act: -0.1700
Data Index: 8260777 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.8666. Min Act: -0.1700
Data Index: 8535823 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.8041. Min Act: -0.1700
Data Index: 392151 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.8041. Min Act: -0.1700
Data Index: 1541781 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.8041. Min Act: -0.1700
Data Index: 8598621 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.8041. Min Act: -0.1700
Data Index: 7440641 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.8041. Min Act: -0.1700
Data Index: 3932709 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.8041. Min Act: -0.1700
Data Index: 3724818 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5541. Min Range: -9.5541
Max Act: 8.7416. Min Act: -0.1700
Data Index: 169683 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19