Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 985 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.2088. Min Act: -0.1700
Data Index: 3788423 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.1463. Min Act: -0.1700
Data Index: 4052419 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.1463. Min Act: -0.1700
Data Index: 1200991 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.1151. Min Act: -0.1700
Data Index: 3862555 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.1151. Min Act: -0.1700
Data Index: 1008387 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.1463. Min Act: -0.1700
Data Index: 3453527 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.1151. Min Act: -0.1700
Data Index: 432737 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.1151. Min Act: -0.1700
Data Index: 1108299 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.0838. Min Act: -0.1700
Data Index: 3085581 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.0526. Min Act: -0.1700
Data Index: 2169924 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.0526. Min Act: -0.1700
Data Index: 5454297 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.0213. Min Act: -0.1700
Data Index: 2901358 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2088. Min Range: -5.2088
Max Act: 5.0526. Min Act: -0.1700
Data Index: 8013128 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2088. Min Range: -5.2088
Max Act: 4.9901. Min Act: -0.1700
Data Index: 2368360 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2088. Min Range: -5.2088
Max Act: 4.9901. Min Act: -0.1700
Data Index: 438685 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2088. Min Range: -5.2088
Max Act: 4.9588. Min Act: -0.1700
Data Index: 2929478 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2088. Min Range: -5.2088
Max Act: 4.9588. Min Act: -0.1700
Data Index: 5873885 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2088. Min Range: -5.2088
Max Act: 4.9588. Min Act: -0.1700
Data Index: 1080134 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2088. Min Range: -5.2088
Max Act: 4.9588. Min Act: -0.1700
Data Index: 8205498 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2088. Min Range: -5.2088
Max Act: 4.9276. Min Act: -0.1700
Data Index: 469399 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19