Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4495. Min Range: -7.4495
Max Act: 7.4495. Min Act: -0.1700
Data Index: 7674210 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4495. Min Range: -7.4495
Max Act: 7.0120. Min Act: -0.1700
Data Index: 7940459 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.9495. Min Act: -0.1700
Data Index: 2671161 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.9183. Min Act: -0.1700
Data Index: 2287496 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.8558. Min Act: -0.1700
Data Index: 5517963 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.8245. Min Act: -0.1700
Data Index: 478990 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.8245. Min Act: -0.1700
Data Index: 8361405 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7620. Min Act: -0.1700
Data Index: 640419 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7933. Min Act: -0.1700
Data Index: 4132260 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7933. Min Act: -0.1700
Data Index: 4019367 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7620. Min Act: -0.1700
Data Index: 2707351 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7620. Min Act: -0.1700
Data Index: 6520282 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7620. Min Act: -0.1700
Data Index: 533557 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7308. Min Act: -0.1700
Data Index: 2995174 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7308. Min Act: -0.1700
Data Index: 7820643 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7308. Min Act: -0.1700
Data Index: 181878 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7308. Min Act: -0.1700
Data Index: 4584278 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7308. Min Act: -0.1700
Data Index: 3665928 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7308. Min Act: -0.1700
Data Index: 4367379 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4495. Min Range: -7.4495
Max Act: 6.7308. Min Act: -0.1700
Data Index: 2807230 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19