Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1294 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.6545. Min Act: -0.1700
Data Index: 5910945 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.6232. Min Act: -0.1700
Data Index: 887148 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.5920. Min Act: -0.1700
Data Index: 843715 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.5607. Min Act: -0.1700
Data Index: 5826337 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.5607. Min Act: -0.1700
Data Index: 1641624 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.5607. Min Act: -0.1700
Data Index: 8016883 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.5295. Min Act: -0.1700
Data Index: 8005930 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.5295. Min Act: -0.1700
Data Index: 6525002 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5178267 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4982. Min Act: -0.1700
Data Index: 3298308 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4982. Min Act: -0.1700
Data Index: 6785406 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4982. Min Act: -0.1700
Data Index: 4084059 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 467266 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 100029 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 1575437 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 7831559 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5937556 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5176178 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 2128566 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5055952 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19