Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3928. Min Range: -7.3928
Max Act: 7.3928. Min Act: -0.1700
Data Index: 7651308 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3928. Min Range: -7.3928
Max Act: 7.3303. Min Act: -0.1700
Data Index: 8208258 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3928. Min Range: -7.3928
Max Act: 7.1115. Min Act: -0.1700
Data Index: 4813780 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3928. Min Range: -7.3928
Max Act: 7.1115. Min Act: -0.1700
Data Index: 7418711 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3928. Min Range: -7.3928
Max Act: 7.1115. Min Act: -0.1700
Data Index: 7840009 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.9865. Min Act: -0.1700
Data Index: 8104856 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.9553. Min Act: -0.1700
Data Index: 301114 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8928. Min Act: -0.1700
Data Index: 4898494 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8928. Min Act: -0.1700
Data Index: 5931742 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8928. Min Act: -0.1700
Data Index: 2542135 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8615. Min Act: -0.1700
Data Index: 1030026 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8615. Min Act: -0.1700
Data Index: 2077243 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8615. Min Act: -0.1700
Data Index: 370447 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8615. Min Act: -0.1700
Data Index: 6604668 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8615. Min Act: -0.1700
Data Index: 57452 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8303. Min Act: -0.1700
Data Index: 6445351 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.8303. Min Act: -0.1700
Data Index: 510542 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.7990. Min Act: -0.1700
Data Index: 4455325 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.7678. Min Act: -0.1700
Data Index: 6570795 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3928. Min Range: -7.3928
Max Act: 6.7678. Min Act: -0.1700
Data Index: 4519774 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19