Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.2817. Min Act: -0.1700
Data Index: 4401856 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.1880. Min Act: -0.1700
Data Index: 4770630 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.1880. Min Act: -0.1700
Data Index: 2005049 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.1567. Min Act: -0.1700
Data Index: 3142717 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.1567. Min Act: -0.1700
Data Index: 3014230 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.1567. Min Act: -0.1700
Data Index: 7500679 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.1255. Min Act: -0.1700
Data Index: 8217690 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.1255. Min Act: -0.1700
Data Index: 7569096 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.1255. Min Act: -0.1700
Data Index: 4672218 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.1255. Min Act: -0.1700
Data Index: 5771376 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0629. Min Act: -0.1700
Data Index: 3555941 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0942. Min Act: -0.1700
Data Index: 2570893 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0629. Min Act: -0.1700
Data Index: 6169553 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0942. Min Act: -0.1700
Data Index: 1947598 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0942. Min Act: -0.1700
Data Index: 2635332 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0942. Min Act: -0.1700
Data Index: 6616843 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0942. Min Act: -0.1700
Data Index: 4559248 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0942. Min Act: -0.1700
Data Index: 4474307 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0942. Min Act: -0.1700
Data Index: 2839721 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2817. Min Range: -4.2817
Max Act: 4.0942. Min Act: -0.1700
Data Index: 4977969 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19