Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.9279. Min Act: -0.1700
Data Index: 8443599 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.8966. Min Act: -0.1700
Data Index: 8223109 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.7716. Min Act: -0.1700
Data Index: 1357807 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.7091. Min Act: -0.1700
Data Index: 8093167 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6779. Min Act: -0.1700
Data Index: 3325762 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6779. Min Act: -0.1700
Data Index: 6191602 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6466. Min Act: -0.1700
Data Index: 4146453 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6466. Min Act: -0.1700
Data Index: 2438851 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6466. Min Act: -0.1700
Data Index: 412905 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6154. Min Act: -0.1700
Data Index: 5168296 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6466. Min Act: -0.1700
Data Index: 792284 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6154. Min Act: -0.1700
Data Index: 6864101 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.6154. Min Act: -0.1700
Data Index: 8829099 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5841. Min Act: -0.1700
Data Index: 5804646 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5841. Min Act: -0.1700
Data Index: 8637259 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5529. Min Act: -0.1700
Data Index: 1774325 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5216. Min Act: -0.1700
Data Index: 1233642 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5529. Min Act: -0.1700
Data Index: 5807083 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5529. Min Act: -0.1700
Data Index: 5082482 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9279. Min Range: -4.9279
Max Act: 4.5529. Min Act: -0.1700
Data Index: 3088270 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19