Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4775 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.6107. Min Act: -0.1700
Data Index: 614674 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.5795. Min Act: -0.1700
Data Index: 4439769 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.5482. Min Act: -0.1700
Data Index: 7828331 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.5170. Min Act: -0.1700
Data Index: 8456597 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.4857. Min Act: -0.1700
Data Index: 5944675 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.4232. Min Act: -0.1700
Data Index: 1492970 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.2982. Min Act: -0.1700
Data Index: 4945193 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.3295. Min Act: -0.1700
Data Index: 2699796 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.2982. Min Act: -0.1700
Data Index: 6533062 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.2982. Min Act: -0.1700
Data Index: 2875778 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.2670. Min Act: -0.1700
Data Index: 3576710 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.2670. Min Act: -0.1700
Data Index: 4392545 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.2045. Min Act: -0.1700
Data Index: 4945355 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.2045. Min Act: -0.1700
Data Index: 7966396 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.2357. Min Act: -0.1700
Data Index: 6047939 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.1732. Min Act: -0.1700
Data Index: 6741574 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.1420. Min Act: -0.1700
Data Index: 3958600 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.1420. Min Act: -0.1700
Data Index: 6065135 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.1420. Min Act: -0.1700
Data Index: 8087476 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6107. Min Range: -7.6107
Max Act: 7.1420. Min Act: -0.1700
Data Index: 568553 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #19