Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4724 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.5612. Min Act: -0.1700
Data Index: 5141695 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.4675. Min Act: -0.1700
Data Index: 4577363 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.4675. Min Act: -0.1700
Data Index: 8601850 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.4050. Min Act: -0.1700
Data Index: 4445544 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3737. Min Act: -0.1700
Data Index: 1620209 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3737. Min Act: -0.1700
Data Index: 5050551 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3737. Min Act: -0.1700
Data Index: 2046927 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3425. Min Act: -0.1700
Data Index: 4979051 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3425. Min Act: -0.1700
Data Index: 2794318 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3425. Min Act: -0.1700
Data Index: 4922612 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3112. Min Act: -0.1700
Data Index: 7750092 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3112. Min Act: -0.1700
Data Index: 6307541 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3112. Min Act: -0.1700
Data Index: 1312461 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.3112. Min Act: -0.1700
Data Index: 2289579 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.2800. Min Act: -0.1700
Data Index: 7512364 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.2800. Min Act: -0.1700
Data Index: 2431536 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.2800. Min Act: -0.1700
Data Index: 4135080 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.2487. Min Act: -0.1700
Data Index: 6843708 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.2487. Min Act: -0.1700
Data Index: 8628017 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5612. Min Range: -6.5612
Max Act: 6.2487. Min Act: -0.1700
Data Index: 8566076 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19