Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1430 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.4948. Min Act: -0.1700
Data Index: 4810889 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.4323. Min Act: -0.1700
Data Index: 204530 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.3698. Min Act: -0.1700
Data Index: 8639051 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.3698. Min Act: -0.1700
Data Index: 5785950 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.3073. Min Act: -0.1700
Data Index: 5698004 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.2448. Min Act: -0.1700
Data Index: 3563844 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.1823. Min Act: -0.1700
Data Index: 555357 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.1823. Min Act: -0.1700
Data Index: 307916 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.0573. Min Act: -0.1700
Data Index: 5535735 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.0573. Min Act: -0.1700
Data Index: 1717435 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.0573. Min Act: -0.1700
Data Index: 1085480 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4948. Min Range: -9.4948
Max Act: 9.0573. Min Act: -0.1700
Data Index: 4200270 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4948. Min Range: -9.4948
Max Act: 8.9948. Min Act: -0.1700
Data Index: 6184428 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4948. Min Range: -9.4948
Max Act: 8.9948. Min Act: -0.1700
Data Index: 622524 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4948. Min Range: -9.4948
Max Act: 8.9948. Min Act: -0.1700
Data Index: 61971 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4948. Min Range: -9.4948
Max Act: 8.9948. Min Act: -0.1700
Data Index: 4654717 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4948. Min Range: -9.4948
Max Act: 8.8698. Min Act: -0.1700
Data Index: 4753745 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4948. Min Range: -9.4948
Max Act: 8.9323. Min Act: -0.1700
Data Index: 1345486 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4948. Min Range: -9.4948
Max Act: 8.9323. Min Act: -0.1700
Data Index: 4996614 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4948. Min Range: -9.4948
Max Act: 8.9323. Min Act: -0.1700
Data Index: 1131463 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19