Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6310. Min Range: -8.6310
Max Act: 8.6310. Min Act: -0.1700
Data Index: 2296646 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.7247. Min Act: -0.1700
Data Index: 8405312 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.6622. Min Act: -0.1700
Data Index: 4087493 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.6622. Min Act: -0.1700
Data Index: 3665083 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.6310. Min Act: -0.1700
Data Index: 8790017 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.5997. Min Act: -0.1700
Data Index: 1336023 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.5060. Min Act: -0.1700
Data Index: 422618 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.4435. Min Act: -0.1700
Data Index: 4433195 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.3810. Min Act: -0.1700
Data Index: 1206063 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.4122. Min Act: -0.1700
Data Index: 3971185 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.3497. Min Act: -0.1700
Data Index: 2967682 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.3497. Min Act: -0.1700
Data Index: 5107725 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.2872. Min Act: -0.1700
Data Index: 3000821 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.2560. Min Act: -0.1700
Data Index: 1791863 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.2560. Min Act: -0.1700
Data Index: 4955822 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.2560. Min Act: -0.1700
Data Index: 6933678 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.2560. Min Act: -0.1700
Data Index: 5073217 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.2247. Min Act: -0.1700
Data Index: 4167792 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.2872. Min Act: -0.1700
Data Index: 6333378 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6310. Min Range: -8.6310
Max Act: 7.2872. Min Act: -0.1700
Data Index: 5438286 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19