Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6036 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.7389. Min Act: -0.1700
Data Index: 2355311 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.6607. Min Act: -0.1700
Data Index: 6343013 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.6607. Min Act: -0.1700
Data Index: 360081 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.6450. Min Act: -0.1700
Data Index: 5491545 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.6294. Min Act: -0.1700
Data Index: 4006592 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.5981. Min Act: -0.1700
Data Index: 6397244 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.5981. Min Act: -0.1700
Data Index: 6308971 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.5355. Min Act: -0.1700
Data Index: 2137411 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4885. Min Act: -0.1700
Data Index: 4786466 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4885. Min Act: -0.1700
Data Index: 878959 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4415. Min Act: -0.1700
Data Index: 6426650 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4258. Min Act: -0.1700
Data Index: 5735371 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4258. Min Act: -0.1700
Data Index: 3318677 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4258. Min Act: -0.1700
Data Index: 2697126 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4101. Min Act: -0.1700
Data Index: 8574884 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4101. Min Act: -0.1700
Data Index: 2388772 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4101. Min Act: -0.1700
Data Index: 874869 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.4101. Min Act: -0.1700
Data Index: 4668897 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.3788. Min Act: -0.1700
Data Index: 2025188 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7389. Min Range: -3.7389
Max Act: 3.3788. Min Act: -0.1700
Data Index: 5651822 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19