Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0214. Min Range: -7.0214
Max Act: 7.0214. Min Act: -0.1700
Data Index: 7244266 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.7714. Min Act: -0.1700
Data Index: 4190144 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.6152. Min Act: -0.1700
Data Index: 5115800 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.5527. Min Act: -0.1700
Data Index: 8667691 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.5214. Min Act: -0.1700
Data Index: 520941 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.5214. Min Act: -0.1700
Data Index: 7803886 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.4902. Min Act: -0.1700
Data Index: 2914020 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.4589. Min Act: -0.1700
Data Index: 5117096 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.4277. Min Act: -0.1700
Data Index: 5586394 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.4277. Min Act: -0.1700
Data Index: 4581101 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.3964. Min Act: -0.1700
Data Index: 2129566 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.3964. Min Act: -0.1700
Data Index: 4911592 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.3652. Min Act: -0.1700
Data Index: 3649483 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.3964. Min Act: -0.1700
Data Index: 6246500 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.3652. Min Act: -0.1700
Data Index: 3797981 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.3652. Min Act: -0.1700
Data Index: 8465375 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.3652. Min Act: -0.1700
Data Index: 113045 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.3652. Min Act: -0.1700
Data Index: 497523 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.3027. Min Act: -0.1700
Data Index: 3705096 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0214. Min Range: -7.0214
Max Act: 6.2714. Min Act: -0.1700
Data Index: 6337921 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19