Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.9312. Min Act: -0.1700
Data Index: 8750554 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.8687. Min Act: -0.1700
Data Index: 4655501 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.7124. Min Act: -0.1700
Data Index: 974585 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.6812. Min Act: -0.1700
Data Index: 4381836 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.5249. Min Act: -0.1700
Data Index: 928174 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.4624. Min Act: -0.1700
Data Index: 7622448 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.4312. Min Act: -0.1700
Data Index: 80239 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.3999. Min Act: -0.1700
Data Index: 8750551 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.3687. Min Act: -0.1700
Data Index: 1643352 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.2749. Min Act: -0.1700
Data Index: 8684368 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.2437. Min Act: -0.1700
Data Index: 5777318 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.1812. Min Act: -0.1700
Data Index: 3262717 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.1499. Min Act: -0.1699
Data Index: 3083225 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.1499. Min Act: -0.1700
Data Index: 1198700 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.1499. Min Act: -0.1700
Data Index: 342812 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.0874. Min Act: -0.1700
Data Index: 676169 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.1187. Min Act: -0.1700
Data Index: 1584389 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.1187. Min Act: -0.1700
Data Index: 3687639 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.1187. Min Act: -0.1700
Data Index: 2042525 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9312. Min Range: -7.9312
Max Act: 7.0874. Min Act: -0.1700
Data Index: 5730469 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19