Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2974. Min Range: -11.2974
Max Act: 11.2974. Min Act: -0.1700
Data Index: 4379910 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2974. Min Range: -11.2974
Max Act: 11.1724. Min Act: -0.1700
Data Index: 2645785 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2974. Min Range: -11.2974
Max Act: 11.1099. Min Act: -0.1700
Data Index: 718006 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2974. Min Range: -11.2974
Max Act: 11.1099. Min Act: -0.1700
Data Index: 3066106 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2974. Min Range: -11.2974
Max Act: 11.1099. Min Act: -0.1700
Data Index: 2573125 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2974. Min Range: -11.2974
Max Act: 11.0474. Min Act: -0.1700
Data Index: 1654879 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2974. Min Range: -11.2974
Max Act: 11.0474. Min Act: -0.1700
Data Index: 1654880 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2974. Min Range: -11.2974
Max Act: 11.0474. Min Act: -0.1700
Data Index: 5921597 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2974. Min Range: -11.2974
Max Act: 11.0474. Min Act: -0.1700
Data Index: 4281245 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.9849. Min Act: -0.1700
Data Index: 1618251 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.9849. Min Act: -0.1700
Data Index: 6526812 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.9849. Min Act: -0.1700
Data Index: 4281246 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.9224. Min Act: -0.1700
Data Index: 7694838 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.9224. Min Act: -0.1700
Data Index: 3066108 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.9224. Min Act: -0.1700
Data Index: 4379909 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.9224. Min Act: -0.1700
Data Index: 1654881 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.8599. Min Act: -0.1700
Data Index: 4573444 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.8599. Min Act: -0.1700
Data Index: 2046607 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.8599. Min Act: -0.1700
Data Index: 6032753 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2974. Min Range: -11.2974
Max Act: 10.7974. Min Act: -0.1700
Data Index: 2046606 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19