Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5128 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.7335. Min Act: -0.1700
Data Index: 4854731 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.7335. Min Act: -0.1700
Data Index: 8453809 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.7335. Min Act: -0.1700
Data Index: 2614122 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.6710. Min Act: -0.1700
Data Index: 3000186 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.6398. Min Act: -0.1700
Data Index: 1868702 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.6085. Min Act: -0.1700
Data Index: 3189934 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5773. Min Act: -0.1700
Data Index: 2511043 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5460. Min Act: -0.1700
Data Index: 7845992 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5460. Min Act: -0.1700
Data Index: 765839 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5460. Min Act: -0.1700
Data Index: 979200 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5460. Min Act: -0.1700
Data Index: 6751552 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5460. Min Act: -0.1700
Data Index: 266129 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5460. Min Act: -0.1700
Data Index: 7239295 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5148. Min Act: -0.1700
Data Index: 748173 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5148. Min Act: -0.1700
Data Index: 7415221 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5148. Min Act: -0.1700
Data Index: 4104214 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5148. Min Act: -0.1700
Data Index: 2489923 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5148. Min Act: -0.1700
Data Index: 6496886 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.4835. Min Act: -0.1700
Data Index: 1272272 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7335. Min Range: -4.7335
Max Act: 4.5148. Min Act: -0.1700
Data Index: 954028 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19