Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 501 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9711. Min Range: -7.9711
Max Act: 7.9711. Min Act: -0.1700
Data Index: 1299478 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9711. Min Range: -7.9711
Max Act: 7.2524. Min Act: -0.1700
Data Index: 2947732 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9711. Min Range: -7.9711
Max Act: 7.1586. Min Act: -0.1700
Data Index: 8116124 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.9711. Min Act: -0.1700
Data Index: 2529931 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.9711. Min Act: -0.1700
Data Index: 6878842 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.8774. Min Act: -0.1700
Data Index: 3066165 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.8461. Min Act: -0.1700
Data Index: 5015736 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.8461. Min Act: -0.1700
Data Index: 7998378 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.8461. Min Act: -0.1700
Data Index: 274441 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.8149. Min Act: -0.1700
Data Index: 1768595 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.7836. Min Act: -0.1700
Data Index: 2621096 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.7836. Min Act: -0.1700
Data Index: 127666 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.7524. Min Act: -0.1700
Data Index: 4453945 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.7524. Min Act: -0.1700
Data Index: 3279164 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.7211. Min Act: -0.1700
Data Index: 1173488 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.6899. Min Act: -0.1700
Data Index: 5114891 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.6274. Min Act: -0.1700
Data Index: 93942 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.6899. Min Act: -0.1700
Data Index: 6057886 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.6586. Min Act: -0.1700
Data Index: 5316889 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9711. Min Range: -7.9711
Max Act: 6.6586. Min Act: -0.1700
Data Index: 2952433 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19