Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1141 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2561. Min Range: -4.2561
Max Act: 4.2561. Min Act: -0.1700
Data Index: 2252775 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2561. Min Range: -4.2561
Max Act: 4.2249. Min Act: -0.1700
Data Index: 3252168 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2561. Min Range: -4.2561
Max Act: 4.1624. Min Act: -0.1700
Data Index: 7883952 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2561. Min Range: -4.2561
Max Act: 4.0999. Min Act: -0.1700
Data Index: 2506105 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2561. Min Range: -4.2561
Max Act: 4.1311. Min Act: -0.1700
Data Index: 8655219 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2561. Min Range: -4.2561
Max Act: 4.0686. Min Act: -0.1700
Data Index: 966831 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2561. Min Range: -4.2561
Max Act: 4.0061. Min Act: -0.1700
Data Index: 3422284 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9748. Min Act: -0.1700
Data Index: 8168598 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2561. Min Range: -4.2561
Max Act: 4.0061. Min Act: -0.1700
Data Index: 6445816 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9748. Min Act: -0.1700
Data Index: 5552942 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9436. Min Act: -0.1700
Data Index: 2653997 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9748. Min Act: -0.1700
Data Index: 1309507 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9748. Min Act: -0.1700
Data Index: 8504102 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9436. Min Act: -0.1700
Data Index: 3899455 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9123. Min Act: -0.1700
Data Index: 2186234 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9123. Min Act: -0.1700
Data Index: 5880895 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9123. Min Act: -0.1700
Data Index: 4948527 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9123. Min Act: -0.1700
Data Index: 4983474 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9123. Min Act: -0.1700
Data Index: 2131753 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2561. Min Range: -4.2561
Max Act: 3.9123. Min Act: -0.1700
Data Index: 4981045 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19