Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5845 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.9456. Min Act: -0.1700
Data Index: 5511515 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.9143. Min Act: -0.1700
Data Index: 1384721 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.8831. Min Act: -0.1700
Data Index: 4350887 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.8518. Min Act: -0.1700
Data Index: 6445579 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.8518. Min Act: -0.1700
Data Index: 5264425 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.7893. Min Act: -0.1700
Data Index: 3738758 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.7893. Min Act: -0.1700
Data Index: 5335694 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.7581. Min Act: -0.1700
Data Index: 4018097 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.7268. Min Act: -0.1700
Data Index: 325241 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.7268. Min Act: -0.1700
Data Index: 979702 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.6956. Min Act: -0.1700
Data Index: 4009249 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.6643. Min Act: -0.1700
Data Index: 8774540 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.6956. Min Act: -0.1700
Data Index: 3505325 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.6956. Min Act: -0.1700
Data Index: 8285721 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.7268. Min Act: -0.1700
Data Index: 2599668 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.6956. Min Act: -0.1700
Data Index: 1541324 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.6956. Min Act: -0.1700
Data Index: 652024 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.6643. Min Act: -0.1700
Data Index: 6593172 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.6643. Min Act: -0.1700
Data Index: 44581 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9456. Min Range: -5.9456
Max Act: 5.6331. Min Act: -0.1700
Data Index: 5641979 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19