Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2664. Min Range: -6.2664
Max Act: 6.2664. Min Act: -0.1700
Data Index: 4508415 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.8289. Min Act: -0.1700
Data Index: 3700699 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.7039. Min Act: -0.1700
Data Index: 4801208 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.6414. Min Act: -0.1700
Data Index: 7578827 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.6414. Min Act: -0.1700
Data Index: 1939189 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.6414. Min Act: -0.1700
Data Index: 8206537 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.6101. Min Act: -0.1700
Data Index: 7409845 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.5476. Min Act: -0.1700
Data Index: 6386798 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.5164. Min Act: -0.1700
Data Index: 426176 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.5789. Min Act: -0.1700
Data Index: 2615695 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.5164. Min Act: -0.1700
Data Index: 8688794 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.4851. Min Act: -0.1700
Data Index: 7060075 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.4226. Min Act: -0.1700
Data Index: 4156276 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.3914. Min Act: -0.1700
Data Index: 5132314 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.3914. Min Act: -0.1700
Data Index: 4119757 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.3601. Min Act: -0.1700
Data Index: 445545 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.3601. Min Act: -0.1700
Data Index: 507880 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.3289. Min Act: -0.1700
Data Index: 7793308 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.3289. Min Act: -0.1700
Data Index: 6120362 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2664. Min Range: -6.2664
Max Act: 5.3289. Min Act: -0.1700
Data Index: 1296811 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19