Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5392 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.9672. Min Act: -0.1700
Data Index: 3509475 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.7797. Min Act: -0.1700
Data Index: 7095674 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.7484. Min Act: -0.1700
Data Index: 5834118 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.6547. Min Act: -0.1700
Data Index: 7490922 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.6234. Min Act: -0.1700
Data Index: 3509474 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.5922. Min Act: -0.1700
Data Index: 8027534 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.5922. Min Act: -0.1700
Data Index: 2966773 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.5297. Min Act: -0.1700
Data Index: 2966775 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.5297. Min Act: -0.1700
Data Index: 4088574 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.4672. Min Act: -0.1700
Data Index: 8503827 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.4672. Min Act: -0.1700
Data Index: 5697261 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.4672. Min Act: -0.1700
Data Index: 5825334 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.4359. Min Act: -0.1700
Data Index: 3662436 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.4359. Min Act: -0.1700
Data Index: 7103064 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.3109. Min Act: -0.1700
Data Index: 4245510 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.3422. Min Act: -0.1700
Data Index: 5247987 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.3109. Min Act: -0.1700
Data Index: 4210711 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.3109. Min Act: -0.1700
Data Index: 7219365 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.2797. Min Act: -0.1700
Data Index: 92620 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9672. Min Range: -7.9672
Max Act: 7.2797. Min Act: -0.1700
Data Index: 6672747 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19