Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.6229. Min Act: -0.1700
Data Index: 6022966 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.2479. Min Act: -0.1700
Data Index: 6013287 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.2479. Min Act: -0.1700
Data Index: 7847872 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.2167. Min Act: -0.1700
Data Index: 6510145 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.1854. Min Act: -0.1700
Data Index: 7686098 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.1854. Min Act: -0.1700
Data Index: 6117770 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.1854. Min Act: -0.1700
Data Index: 5125825 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.1854. Min Act: -0.1700
Data Index: 7309371 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.1229. Min Act: -0.1700
Data Index: 2809854 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.1229. Min Act: -0.1700
Data Index: 2438598 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.1542. Min Act: -0.1700
Data Index: 5349063 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.0917. Min Act: -0.1700
Data Index: 1537825 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.0917. Min Act: -0.1700
Data Index: 69069 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.0604. Min Act: -0.1700
Data Index: 1602699 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6229. Min Range: -6.6229
Max Act: 6.0292. Min Act: -0.1700
Data Index: 7473870 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6229. Min Range: -6.6229
Max Act: 5.9979. Min Act: -0.1700
Data Index: 5086040 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6229. Min Range: -6.6229
Max Act: 5.9667. Min Act: -0.1700
Data Index: 1246633 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6229. Min Range: -6.6229
Max Act: 5.9354. Min Act: -0.1700
Data Index: 2455683 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6229. Min Range: -6.6229
Max Act: 5.9354. Min Act: -0.1700
Data Index: 6432174 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6229. Min Range: -6.6229
Max Act: 5.9354. Min Act: -0.1700
Data Index: 1050571 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19