Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0252. Min Range: -9.0252
Max Act: 9.0252. Min Act: -0.1700
Data Index: 2984144 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.8377. Min Act: -0.1700
Data Index: 6403035 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.7127. Min Act: -0.1700
Data Index: 5377495 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.6502. Min Act: -0.1700
Data Index: 577723 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.5877. Min Act: -0.1700
Data Index: 8278915 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.5877. Min Act: -0.1700
Data Index: 7300615 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.5877. Min Act: -0.1700
Data Index: 262740 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.5877. Min Act: -0.1700
Data Index: 837023 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.5252. Min Act: -0.1700
Data Index: 6174264 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.4627. Min Act: -0.1700
Data Index: 944894 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.4002. Min Act: -0.1700
Data Index: 5122661 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.4002. Min Act: -0.1700
Data Index: 4099545 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.4002. Min Act: -0.1700
Data Index: 4589389 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.4002. Min Act: -0.1700
Data Index: 1194582 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.4002. Min Act: -0.1700
Data Index: 1231150 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.4002. Min Act: -0.1700
Data Index: 3852928 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.3377. Min Act: -0.1700
Data Index: 4079631 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.3377. Min Act: -0.1700
Data Index: 4582269 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.3377. Min Act: -0.1700
Data Index: 6808859 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0252. Min Range: -9.0252
Max Act: 8.3377. Min Act: -0.1700
Data Index: 1439383 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19