Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1775 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0921. Min Act: -0.1645
Data Index: 889885 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0921. Min Act: -0.1698
Data Index: 437315 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.1546. Min Act: -0.1694
Data Index: 2324039 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0921. Min Act: -0.1699
Data Index: 8203951 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0921. Min Act: -0.1698
Data Index: 1740037 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0921. Min Act: -0.1693
Data Index: 8796197 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0921. Min Act: -0.1698
Data Index: 3602541 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0296. Min Act: -0.1690
Data Index: 7325528 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0296. Min Act: -0.1468
Data Index: 4445648 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0296. Min Act: -0.1700
Data Index: 2403886 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.1546. Min Range: -14.1546
Max Act: 14.0296. Min Act: -0.1700
Data Index: 4173384 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.1546. Min Range: -14.1546
Max Act: 13.9046. Min Act: -0.1485
Data Index: 5436970 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.1546. Min Range: -14.1546
Max Act: 13.9671. Min Act: -0.1697
Data Index: 5438681 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.1546. Min Range: -14.1546
Max Act: 13.9671. Min Act: -0.1335
Data Index: 175148 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.1546. Min Range: -14.1546
Max Act: 13.9671. Min Act: -0.1700
Data Index: 294720 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.1546. Min Range: -14.1546
Max Act: 13.9671. Min Act: -0.1694
Data Index: 4377367 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.1546. Min Range: -14.1546
Max Act: 13.9046. Min Act: -0.1700
Data Index: 627914 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.1546. Min Range: -14.1546
Max Act: 13.9046. Min Act: -0.1700
Data Index: 3841406 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.1546. Min Range: -14.1546
Max Act: 13.9046. Min Act: -0.1698
Data Index: 5078030 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.1546. Min Range: -14.1546
Max Act: 13.9046. Min Act: -0.1675
Data Index: 4162625 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19