Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 303 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.6436. Min Act: -0.1700
Data Index: 6710230 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.6123. Min Act: -0.1700
Data Index: 8824179 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.5186. Min Act: -0.1700
Data Index: 3125443 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.4248. Min Act: -0.1700
Data Index: 4908735 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.3311. Min Act: -0.1700
Data Index: 6182137 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.2998. Min Act: -0.1700
Data Index: 3790425 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.2686. Min Act: -0.1700
Data Index: 4913815 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.2373. Min Act: -0.1700
Data Index: 6792343 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.2061. Min Act: -0.1700
Data Index: 4717560 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.1748. Min Act: -0.1700
Data Index: 4717567 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.1436. Min Act: -0.1700
Data Index: 6363292 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.1436. Min Act: -0.1700
Data Index: 7741134 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.1436. Min Act: -0.1700
Data Index: 4717555 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.0811. Min Act: -0.1700
Data Index: 8342274 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.0811. Min Act: -0.1700
Data Index: 7218898 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.0811. Min Act: -0.1700
Data Index: 2633127 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.0811. Min Act: -0.1700
Data Index: 985612 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.0811. Min Act: -0.1700
Data Index: 6433634 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.0811. Min Act: -0.1700
Data Index: 1055120 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6436. Min Range: -5.6436
Max Act: 5.0811. Min Act: -0.1700
Data Index: 912467 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19