Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 194 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.6191. Min Act: -0.1698
Data Index: 3061541 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5876. Min Act: -0.1698
Data Index: 3689312 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.6033. Min Act: -0.1694
Data Index: 6924793 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5876. Min Act: -0.1699
Data Index: 5183601 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5876. Min Act: -0.1700
Data Index: 10932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5876. Min Act: -0.1700
Data Index: 335393 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5876. Min Act: -0.1700
Data Index: 2051261 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5876. Min Act: -0.1699
Data Index: 2522845 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.6033. Min Act: -0.1696
Data Index: 6331516 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5798. Min Act: -0.1700
Data Index: 1657597 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5720. Min Act: -0.1700
Data Index: 249194 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5720. Min Act: -0.1700
Data Index: 5989973 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5565. Min Act: -0.1700
Data Index: 3058136 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5565. Min Act: -0.1700
Data Index: 5318446 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5565. Min Act: -0.1699
Data Index: 873701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5565. Min Act: -0.1699
Data Index: 5947932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5565. Min Act: -0.1697
Data Index: 2153322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5565. Min Act: -0.1693
Data Index: 2207968 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5565. Min Act: -0.1700
Data Index: 2042358 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6191. Min Range: -0.6191
Max Act: 0.5488. Min Act: -0.1698
Data Index: 1861331 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19