Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1447 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0586. Min Range: -4.0586
Max Act: 4.0586. Min Act: -0.1700
Data Index: 6196707 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.8710. Min Act: -0.1700
Data Index: 1551555 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.8085. Min Act: -0.1700
Data Index: 8458891 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.7772. Min Act: -0.1700
Data Index: 3081625 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.7459. Min Act: -0.1700
Data Index: 3380825 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.7772. Min Act: -0.1700
Data Index: 5045527 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.7459. Min Act: -0.1700
Data Index: 2882138 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.7459. Min Act: -0.1700
Data Index: 4943483 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.6521. Min Act: -0.1700
Data Index: 7573032 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.6833. Min Act: -0.1700
Data Index: 5740050 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.6208. Min Act: -0.1700
Data Index: 3107571 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.6208. Min Act: -0.1700
Data Index: 5746940 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.5895. Min Act: -0.1700
Data Index: 4160196 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.5895. Min Act: -0.1700
Data Index: 5489860 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.5895. Min Act: -0.1700
Data Index: 6536730 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.5895. Min Act: -0.1700
Data Index: 455668 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.5895. Min Act: -0.1700
Data Index: 5489864 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.5895. Min Act: -0.1700
Data Index: 1285293 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.5895. Min Act: -0.1700
Data Index: 3191781 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0586. Min Range: -4.0586
Max Act: 3.5895. Min Act: -0.1700
Data Index: 5692517 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19