Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1164 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0235. Min Range: -7.0235
Max Act: 7.0235. Min Act: -0.1700
Data Index: 1401076 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0235. Min Range: -7.0235
Max Act: 7.0235. Min Act: -0.1700
Data Index: 5563192 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.9610. Min Act: -0.1700
Data Index: 408508 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.9610. Min Act: -0.1700
Data Index: 7045349 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.9297. Min Act: -0.1700
Data Index: 1881497 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.9297. Min Act: -0.1700
Data Index: 539687 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8985. Min Act: -0.1700
Data Index: 6274469 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8672. Min Act: -0.1700
Data Index: 4838409 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8672. Min Act: -0.1700
Data Index: 7112593 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8360. Min Act: -0.1700
Data Index: 696928 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8360. Min Act: -0.1700
Data Index: 3767560 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8047. Min Act: -0.1700
Data Index: 7241755 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8047. Min Act: -0.1700
Data Index: 7688099 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8360. Min Act: -0.1700
Data Index: 1209142 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.7735. Min Act: -0.1700
Data Index: 1667339 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8047. Min Act: -0.1700
Data Index: 7770518 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.8047. Min Act: -0.1700
Data Index: 6501678 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.7735. Min Act: -0.1700
Data Index: 7579926 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.7735. Min Act: -0.1700
Data Index: 3321489 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0235. Min Range: -7.0235
Max Act: 6.7735. Min Act: -0.1700
Data Index: 6325596 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19