Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5604 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.3542. Min Act: -0.1700
Data Index: 4636437 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.3229. Min Act: -0.1700
Data Index: 3506422 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1979. Min Act: -0.1700
Data Index: 7271556 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.2292. Min Act: -0.1700
Data Index: 3460284 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1667. Min Act: -0.1700
Data Index: 7533926 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1667. Min Act: -0.1700
Data Index: 7690683 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1354. Min Act: -0.1700
Data Index: 4924734 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1667. Min Act: -0.1700
Data Index: 1168084 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1667. Min Act: -0.1700
Data Index: 8424145 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1667. Min Act: -0.1700
Data Index: 7114538 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1354. Min Act: -0.1700
Data Index: 2931969 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1354. Min Act: -0.1700
Data Index: 8223902 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1354. Min Act: -0.1700
Data Index: 96726 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1042. Min Act: -0.1700
Data Index: 1628421 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1042. Min Act: -0.1700
Data Index: 2139578 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1042. Min Act: -0.1700
Data Index: 6993882 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1042. Min Act: -0.1700
Data Index: 3474547 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.1042. Min Act: -0.1700
Data Index: 1575209 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.0729. Min Act: -0.1700
Data Index: 1482476 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3542. Min Range: -5.3542
Max Act: 5.0729. Min Act: -0.1700
Data Index: 6862592 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19