Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2479 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.7603. Min Act: -0.1700
Data Index: 4293641 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.7603. Min Act: -0.1700
Data Index: 6537424 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6977. Min Act: -0.1700
Data Index: 3672220 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6977. Min Act: -0.1700
Data Index: 5933155 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.6040. Min Act: -0.1700
Data Index: 5158425 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5727. Min Act: -0.1700
Data Index: 1024563 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5727. Min Act: -0.1700
Data Index: 119838 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5727. Min Act: -0.1700
Data Index: 4293632 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5727. Min Act: -0.1700
Data Index: 4293656 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5102. Min Act: -0.1700
Data Index: 1652884 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5415. Min Act: -0.1700
Data Index: 2644958 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5102. Min Act: -0.1700
Data Index: 5960738 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5102. Min Act: -0.1700
Data Index: 2284932 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.5102. Min Act: -0.1700
Data Index: 7888249 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4790. Min Act: -0.1700
Data Index: 6365401 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4477. Min Act: -0.1700
Data Index: 3957453 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4165. Min Act: -0.1700
Data Index: 4767799 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4477. Min Act: -0.1700
Data Index: 2118672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4477. Min Act: -0.1700
Data Index: 7430246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7603. Min Range: -4.7603
Max Act: 4.4477. Min Act: -0.1700
Data Index: 2510848 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19