Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2228 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.8282. Min Act: -0.1700
Data Index: 6285858 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.7344. Min Act: -0.1700
Data Index: 6501961 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.7031. Min Act: -0.1700
Data Index: 1466758 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.7344. Min Act: -0.1700
Data Index: 5890916 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6718. Min Act: -0.1700
Data Index: 6984641 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.7031. Min Act: -0.1700
Data Index: 1153604 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6718. Min Act: -0.1700
Data Index: 830264 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6718. Min Act: -0.1700
Data Index: 7784349 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6718. Min Act: -0.1700
Data Index: 8303586 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6405. Min Act: -0.1700
Data Index: 6688553 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6718. Min Act: -0.1700
Data Index: 6027430 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6092. Min Act: -0.1700
Data Index: 7807359 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6092. Min Act: -0.1700
Data Index: 6540170 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6405. Min Act: -0.1700
Data Index: 4553677 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.5935. Min Act: -0.1700
Data Index: 2154818 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.5935. Min Act: -0.1700
Data Index: 721243 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6248. Min Act: -0.1700
Data Index: 7207092 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6092. Min Act: -0.1700
Data Index: 2040330 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.6092. Min Act: -0.1700
Data Index: 221016 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8282. Min Range: -3.8282
Max Act: 3.5935. Min Act: -0.1700
Data Index: 2705630 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19