Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2231 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.7225. Min Act: -0.1700
Data Index: 1120289 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.7538. Min Act: -0.1700
Data Index: 8106705 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.6913. Min Act: -0.1700
Data Index: 4575533 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.6288. Min Act: -0.1700
Data Index: 5410331 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5975. Min Act: -0.1700
Data Index: 6638411 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5975. Min Act: -0.1700
Data Index: 3899253 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5663. Min Act: -0.1700
Data Index: 302999 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 1911197 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 4575534 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 3604503 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 3213933 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 8063057 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 7324174 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 6509299 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5350. Min Act: -0.1700
Data Index: 6800105 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4725. Min Act: -0.1700
Data Index: 317115 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 2169413 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4725. Min Act: -0.1700
Data Index: 5029054 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.5038. Min Act: -0.1700
Data Index: 6015397 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7538. Min Range: -5.7538
Max Act: 5.4725. Min Act: -0.1700
Data Index: 2484787 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19