Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.4141. Min Act: -0.1700
Data Index: 4978452 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.2891. Min Act: -0.1700
Data Index: 209898 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.2891. Min Act: -0.1700
Data Index: 4497392 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.2266. Min Act: -0.1700
Data Index: 1534035 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.2266. Min Act: -0.1700
Data Index: 2660048 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1954. Min Act: -0.1700
Data Index: 4899494 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1954. Min Act: -0.1700
Data Index: 5279722 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.2266. Min Act: -0.1700
Data Index: 3031764 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1641. Min Act: -0.1700
Data Index: 8356251 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1641. Min Act: -0.1700
Data Index: 6069209 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1641. Min Act: -0.1700
Data Index: 3590549 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1641. Min Act: -0.1700
Data Index: 2003262 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1329. Min Act: -0.1700
Data Index: 8440719 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1016. Min Act: -0.1700
Data Index: 4489924 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1329. Min Act: -0.1700
Data Index: 6555421 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1016. Min Act: -0.1700
Data Index: 136670 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1016. Min Act: -0.1700
Data Index: 6087032 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1016. Min Act: -0.1700
Data Index: 3576402 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1016. Min Act: -0.1700
Data Index: 6238910 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4141. Min Range: -5.4141
Max Act: 5.1016. Min Act: -0.1700
Data Index: 6435625 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19