Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2490 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5962. Min Act: -0.1700
Data Index: 1972764 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5962. Min Act: -0.1700
Data Index: 4466648 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5699. Min Act: -0.1700
Data Index: 6028986 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5524. Min Act: -0.1700
Data Index: 8321191 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5612. Min Act: -0.1698
Data Index: 4782146 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5524. Min Act: -0.1700
Data Index: 628941 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5524. Min Act: -0.1700
Data Index: 395375 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5262. Min Act: -0.1700
Data Index: 578876 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5437. Min Act: -0.1700
Data Index: 8754059 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5174. Min Act: -0.1700
Data Index: 4939792 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5262. Min Act: -0.1700
Data Index: 2500097 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5262. Min Act: -0.1697
Data Index: 92349 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5262. Min Act: -0.1700
Data Index: 6677886 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5262. Min Act: -0.1700
Data Index: 2342386 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5174. Min Act: -0.1700
Data Index: 8520874 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5174. Min Act: -0.1700
Data Index: 2155341 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5174. Min Act: -0.1700
Data Index: 7168513 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5174. Min Act: -0.1700
Data Index: 7633192 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5174. Min Act: -0.1700
Data Index: 8477280 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5962. Min Range: -1.5962
Max Act: 1.5262. Min Act: -0.1700
Data Index: 1247453 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19