Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3499 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.6169. Min Act: -0.1700
Data Index: 3266881 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.3668. Min Act: -0.1700
Data Index: 2418739 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.2106. Min Act: -0.1700
Data Index: 6884823 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.2106. Min Act: -0.1700
Data Index: 5285559 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0856. Min Act: -0.1700
Data Index: 3589736 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0856. Min Act: -0.1700
Data Index: 5701693 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0543. Min Act: -0.1700
Data Index: 1927085 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0230. Min Act: -0.1700
Data Index: 1850282 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0543. Min Act: -0.1700
Data Index: 143675 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0543. Min Act: -0.1700
Data Index: 5460155 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0543. Min Act: -0.1700
Data Index: 7101 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0230. Min Act: -0.1700
Data Index: 8042466 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0230. Min Act: -0.1700
Data Index: 3522384 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0230. Min Act: -0.1700
Data Index: 1267354 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6169. Min Range: -4.6169
Max Act: 4.0230. Min Act: -0.1700
Data Index: 1041404 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6169. Min Range: -4.6169
Max Act: 3.9918. Min Act: -0.1700
Data Index: 960852 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6169. Min Range: -4.6169
Max Act: 3.9918. Min Act: -0.1700
Data Index: 5698369 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6169. Min Range: -4.6169
Max Act: 3.9918. Min Act: -0.1700
Data Index: 3276362 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6169. Min Range: -4.6169
Max Act: 3.9918. Min Act: -0.1700
Data Index: 84773 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6169. Min Range: -4.6169
Max Act: 3.9918. Min Act: -0.1700
Data Index: 338013 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19