Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 320 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1916. Min Range: -5.1916
Max Act: 5.1916. Min Act: -0.1700
Data Index: 3949160 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1916. Min Range: -5.1916
Max Act: 5.1603. Min Act: -0.1700
Data Index: 1265682 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1916. Min Range: -5.1916
Max Act: 5.1291. Min Act: -0.1700
Data Index: 4961092 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1916. Min Range: -5.1916
Max Act: 5.0353. Min Act: -0.1700
Data Index: 5666296 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.9728. Min Act: -0.1700
Data Index: 1412711 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.9728. Min Act: -0.1700
Data Index: 3480423 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.9416. Min Act: -0.1700
Data Index: 4566965 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.9416. Min Act: -0.1700
Data Index: 8399115 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.8791. Min Act: -0.1700
Data Index: 3220105 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.8791. Min Act: -0.1700
Data Index: 4333989 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.8478. Min Act: -0.1700
Data Index: 3825829 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.8478. Min Act: -0.1700
Data Index: 6224315 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.8166. Min Act: -0.1700
Data Index: 5025562 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.7853. Min Act: -0.1700
Data Index: 2710099 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.7853. Min Act: -0.1700
Data Index: 501396 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.7853. Min Act: -0.1700
Data Index: 2700087 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.7853. Min Act: -0.1700
Data Index: 587261 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.7853. Min Act: -0.1700
Data Index: 1089332 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.7853. Min Act: -0.1700
Data Index: 2127019 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1916. Min Range: -5.1916
Max Act: 4.7853. Min Act: -0.1700
Data Index: 402783 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19