Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1747 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4232. Min Range: -7.4232
Max Act: 7.4232. Min Act: -0.1700
Data Index: 2425855 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4232. Min Range: -7.4232
Max Act: 7.2982. Min Act: -0.1700
Data Index: 5668637 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4232. Min Range: -7.4232
Max Act: 7.0795. Min Act: -0.1700
Data Index: 267833 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4232. Min Range: -7.4232
Max Act: 7.0482. Min Act: -0.1700
Data Index: 4368317 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4232. Min Range: -7.4232
Max Act: 7.0795. Min Act: -0.1700
Data Index: 7908908 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.9232. Min Act: -0.1700
Data Index: 3287255 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.9232. Min Act: -0.1700
Data Index: 8108808 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.9232. Min Act: -0.1700
Data Index: 2619942 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.8920. Min Act: -0.1700
Data Index: 3765636 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.8607. Min Act: -0.1700
Data Index: 7028865 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.8295. Min Act: -0.1700
Data Index: 4223106 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.8295. Min Act: -0.1700
Data Index: 6978305 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.8295. Min Act: -0.1700
Data Index: 8350920 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.8607. Min Act: -0.1700
Data Index: 3508931 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.7982. Min Act: -0.1700
Data Index: 7873564 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.7982. Min Act: -0.1700
Data Index: 6730576 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.7670. Min Act: -0.1700
Data Index: 1991905 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.7670. Min Act: -0.1700
Data Index: 6173478 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.7045. Min Act: -0.1700
Data Index: 7609470 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4232. Min Range: -7.4232
Max Act: 6.7045. Min Act: -0.1700
Data Index: 1952672 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19