Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2459. Min Range: -4.2459
Max Act: 4.2459. Min Act: -0.1700
Data Index: 8109190 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2459. Min Range: -4.2459
Max Act: 4.0271. Min Act: -0.1700
Data Index: 3578796 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.9646. Min Act: -0.1700
Data Index: 6579940 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.9333. Min Act: -0.1700
Data Index: 1381325 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.9333. Min Act: -0.1700
Data Index: 1098532 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.9333. Min Act: -0.1700
Data Index: 4163383 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.8708. Min Act: -0.1700
Data Index: 3141129 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.8708. Min Act: -0.1700
Data Index: 8411430 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.8395. Min Act: -0.1700
Data Index: 3127932 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.8708. Min Act: -0.1700
Data Index: 8089695 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.7770. Min Act: -0.1700
Data Index: 8038252 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.7770. Min Act: -0.1700
Data Index: 8038253 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.7144. Min Act: -0.1700
Data Index: 947454 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.7457. Min Act: -0.1700
Data Index: 2777583 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.7144. Min Act: -0.1700
Data Index: 8484939 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.7144. Min Act: -0.1700
Data Index: 7598535 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.6988. Min Act: -0.1700
Data Index: 8169296 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.6831. Min Act: -0.1700
Data Index: 1350855 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.6831. Min Act: -0.1700
Data Index: 4639047 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2459. Min Range: -4.2459
Max Act: 3.6518. Min Act: -0.1700
Data Index: 4995770 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19