Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3353 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.5731. Min Act: -0.1700
Data Index: 3595251 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.2606. Min Act: -0.1700
Data Index: 3522882 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.3231. Min Act: -0.1700
Data Index: 5321599 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.2606. Min Act: -0.1700
Data Index: 2500943 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.2606. Min Act: -0.1700
Data Index: 5669547 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.2606. Min Act: -0.1700
Data Index: 5845087 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.1981. Min Act: -0.1700
Data Index: 5544788 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.2606. Min Act: -0.1700
Data Index: 2523852 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.1356. Min Act: -0.1700
Data Index: 5139570 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.0731. Min Act: -0.1700
Data Index: 784261 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.0731. Min Act: -0.1700
Data Index: 3775316 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.0731. Min Act: -0.1700
Data Index: 2808623 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.0731. Min Act: -0.1700
Data Index: 75485 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.0731. Min Act: -0.1700
Data Index: 5844676 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.0106. Min Act: -0.1700
Data Index: 2279602 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.0106. Min Act: -0.1700
Data Index: 8711090 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.0106. Min Act: -0.1700
Data Index: 7600057 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5731. Min Range: -10.5731
Max Act: 10.0106. Min Act: -0.1700
Data Index: 6365012 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5731. Min Range: -10.5731
Max Act: 9.9481. Min Act: -0.1700
Data Index: 2652215 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5731. Min Range: -10.5731
Max Act: 9.9481. Min Act: -0.1700
Data Index: 6137371 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19