Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0649. Min Range: -6.0649
Max Act: 6.0649. Min Act: -0.1700
Data Index: 7868787 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.9086. Min Act: -0.1700
Data Index: 7811096 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.8149. Min Act: -0.1700
Data Index: 1278971 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.7836. Min Act: -0.1700
Data Index: 5175924 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.7211. Min Act: -0.1700
Data Index: 6777484 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.7524. Min Act: -0.1700
Data Index: 894662 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.6586. Min Act: -0.1700
Data Index: 1840656 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.6274. Min Act: -0.1700
Data Index: 6345415 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.6274. Min Act: -0.1700
Data Index: 1083051 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5961. Min Act: -0.1700
Data Index: 2976773 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5961. Min Act: -0.1700
Data Index: 1083052 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5336. Min Act: -0.1700
Data Index: 8022652 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5336. Min Act: -0.1700
Data Index: 8489075 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5336. Min Act: -0.1700
Data Index: 7512267 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5336. Min Act: -0.1700
Data Index: 3406144 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5024. Min Act: -0.1700
Data Index: 2023491 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5024. Min Act: -0.1700
Data Index: 1724250 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5336. Min Act: -0.1700
Data Index: 4176912 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.5024. Min Act: -0.1700
Data Index: 1029002 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0649. Min Range: -6.0649
Max Act: 5.4711. Min Act: -0.1700
Data Index: 6539824 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19