Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3337 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.7916. Min Act: -0.1700
Data Index: 5812662 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.6978. Min Act: -0.1700
Data Index: 5173231 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.6353. Min Act: -0.1700
Data Index: 5851002 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.6041. Min Act: -0.1700
Data Index: 4577528 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.5728. Min Act: -0.1700
Data Index: 1012148 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.5416. Min Act: -0.1700
Data Index: 7936462 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.5416. Min Act: -0.1700
Data Index: 2482668 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.5416. Min Act: -0.1700
Data Index: 6439814 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.5416. Min Act: -0.1700
Data Index: 4818221 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.4166. Min Act: -0.1700
Data Index: 3245621 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.4166. Min Act: -0.1700
Data Index: 4577527 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.4166. Min Act: -0.1700
Data Index: 7419704 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3853. Min Act: -0.1700
Data Index: 5662810 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3541. Min Act: -0.1700
Data Index: 4216700 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3853. Min Act: -0.1700
Data Index: 7168302 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3853. Min Act: -0.1700
Data Index: 1266378 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3541. Min Act: -0.1700
Data Index: 2940324 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3541. Min Act: -0.1700
Data Index: 2649431 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3541. Min Act: -0.1700
Data Index: 8270947 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7916. Min Range: -6.7916
Max Act: 6.3541. Min Act: -0.1700
Data Index: 4314067 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19