Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4602 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4051. Min Range: -5.4051
Max Act: 5.4051. Min Act: -0.1700
Data Index: 1164139 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4051. Min Range: -5.4051
Max Act: 5.3113. Min Act: -0.1700
Data Index: 8783972 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4051. Min Range: -5.4051
Max Act: 5.2488. Min Act: -0.1700
Data Index: 5362364 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4051. Min Range: -5.4051
Max Act: 5.0301. Min Act: -0.1700
Data Index: 4113153 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.9988. Min Act: -0.1700
Data Index: 6834806 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.9988. Min Act: -0.1700
Data Index: 6908730 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.8738. Min Act: -0.1700
Data Index: 7918078 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.9051. Min Act: -0.1700
Data Index: 1334232 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.8426. Min Act: -0.1700
Data Index: 4814282 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.8738. Min Act: -0.1700
Data Index: 5431957 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.8426. Min Act: -0.1700
Data Index: 4801681 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.8113. Min Act: -0.1700
Data Index: 5979949 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.8113. Min Act: -0.1700
Data Index: 4147540 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.8113. Min Act: -0.1700
Data Index: 8458403 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.7488. Min Act: -0.1700
Data Index: 1579614 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.7488. Min Act: -0.1700
Data Index: 4957525 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.7488. Min Act: -0.1700
Data Index: 354083 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.7176. Min Act: -0.1700
Data Index: 5977766 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.7176. Min Act: -0.1700
Data Index: 4105630 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4051. Min Range: -5.4051
Max Act: 4.7176. Min Act: -0.1700
Data Index: 5491499 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19