Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.9310. Min Act: -0.1700
Data Index: 7295920 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.8685. Min Act: -0.1700
Data Index: 1716911 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.7435. Min Act: -0.1700
Data Index: 4080962 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.6497. Min Act: -0.1700
Data Index: 7063220 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.6185. Min Act: -0.1700
Data Index: 2951116 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.6497. Min Act: -0.1700
Data Index: 230405 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.6185. Min Act: -0.1700
Data Index: 1306087 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5872. Min Act: -0.1700
Data Index: 3477242 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5872. Min Act: -0.1700
Data Index: 301597 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5560. Min Act: -0.1700
Data Index: 6212864 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5560. Min Act: -0.1700
Data Index: 494220 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5560. Min Act: -0.1700
Data Index: 8387167 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5560. Min Act: -0.1700
Data Index: 3578967 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5247. Min Act: -0.1700
Data Index: 1315220 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5872. Min Act: -0.1700
Data Index: 2098033 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5247. Min Act: -0.1700
Data Index: 1622483 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.5247. Min Act: -0.1700
Data Index: 3490904 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.4935. Min Act: -0.1700
Data Index: 1709352 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.4935. Min Act: -0.1700
Data Index: 3841077 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9310. Min Range: -4.9310
Max Act: 4.4935. Min Act: -0.1700
Data Index: 6390889 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19