Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.5130. Min Act: -0.1700
Data Index: 462507 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.5130. Min Act: -0.1700
Data Index: 7618131 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.4192. Min Act: -0.1700
Data Index: 6674156 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.3880. Min Act: -0.1700
Data Index: 1199532 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.3880. Min Act: -0.1700
Data Index: 4431751 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.3567. Min Act: -0.1700
Data Index: 3914261 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.3567. Min Act: -0.1700
Data Index: 8567484 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.3255. Min Act: -0.1700
Data Index: 7763223 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.3255. Min Act: -0.1700
Data Index: 2082137 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2942. Min Act: -0.1700
Data Index: 1196910 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2630. Min Act: -0.1700
Data Index: 7396977 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2317. Min Act: -0.1700
Data Index: 2423375 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2630. Min Act: -0.1700
Data Index: 7750533 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2005. Min Act: -0.1700
Data Index: 87511 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2630. Min Act: -0.1700
Data Index: 4319027 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2317. Min Act: -0.1700
Data Index: 7879101 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2317. Min Act: -0.1700
Data Index: 4146219 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2317. Min Act: -0.1700
Data Index: 3107477 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2005. Min Act: -0.1700
Data Index: 2194674 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5130. Min Range: -4.5130
Max Act: 4.2005. Min Act: -0.1700
Data Index: 2366798 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19