Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.8924. Min Act: -0.1700
Data Index: 6977687 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.7362. Min Act: -0.1700
Data Index: 85822 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.7362. Min Act: -0.1700
Data Index: 194783 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.6737. Min Act: -0.1700
Data Index: 2289181 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.6112. Min Act: -0.1700
Data Index: 4972617 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.6112. Min Act: -0.1700
Data Index: 1032363 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.6112. Min Act: -0.1700
Data Index: 1692185 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.5799. Min Act: -0.1700
Data Index: 257884 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.5487. Min Act: -0.1700
Data Index: 4910827 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.5487. Min Act: -0.1700
Data Index: 6566086 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.5174. Min Act: -0.1700
Data Index: 2534719 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.5174. Min Act: -0.1700
Data Index: 8262817 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.5487. Min Act: -0.1700
Data Index: 281648 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.5174. Min Act: -0.1700
Data Index: 2970222 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.5174. Min Act: -0.1700
Data Index: 4398177 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.5174. Min Act: -0.1700
Data Index: 2959590 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.4862. Min Act: -0.1700
Data Index: 1764608 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.4862. Min Act: -0.1700
Data Index: 5707611 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.4237. Min Act: -0.1700
Data Index: 2077197 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8924. Min Range: -6.8924
Max Act: 6.4237. Min Act: -0.1700
Data Index: 4049767 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19