Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3079 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.8334. Min Act: -0.1700
Data Index: 2230186 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3959. Min Act: -0.1700
Data Index: 2268351 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.3022. Min Act: -0.1700
Data Index: 6221604 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.2709. Min Act: -0.1700
Data Index: 4195701 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.2397. Min Act: -0.1700
Data Index: 7225526 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.2397. Min Act: -0.1700
Data Index: 1703227 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.1459. Min Act: -0.1700
Data Index: 5377315 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.1772. Min Act: -0.1700
Data Index: 1992700 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.1772. Min Act: -0.1700
Data Index: 779420 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.1772. Min Act: -0.1700
Data Index: 1555937 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.1459. Min Act: -0.1700
Data Index: 3791995 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.1147. Min Act: -0.1700
Data Index: 4756069 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.1147. Min Act: -0.1700
Data Index: 3784397 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.0834. Min Act: -0.1700
Data Index: 2817951 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.0834. Min Act: -0.1700
Data Index: 265891 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.0522. Min Act: -0.1700
Data Index: 5351820 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.0522. Min Act: -0.1700
Data Index: 6130631 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8334. Min Range: -7.8334
Max Act: 6.9897. Min Act: -0.1700
Data Index: 4098372 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.0209. Min Act: -0.1700
Data Index: 5125060 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8334. Min Range: -7.8334
Max Act: 7.0209. Min Act: -0.1700
Data Index: 3748821 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19