Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2773 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.6217. Min Act: -0.1700
Data Index: 2772558 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.4967. Min Act: -0.1700
Data Index: 4134606 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.3717. Min Act: -0.1700
Data Index: 3888476 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.3717. Min Act: -0.1700
Data Index: 3556176 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.3717. Min Act: -0.1700
Data Index: 2879769 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.2467. Min Act: -0.1700
Data Index: 3218929 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.2467. Min Act: -0.1700
Data Index: 2580982 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.2467. Min Act: -0.1700
Data Index: 5050268 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.1217. Min Act: -0.1700
Data Index: 7234280 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.1217. Min Act: -0.1700
Data Index: 4556398 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.6217. Min Range: -18.6217
Max Act: 17.9967. Min Act: -0.1700
Data Index: 2929676 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.6217. Min Range: -18.6217
Max Act: 18.1217. Min Act: -0.1700
Data Index: 289401 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.6217. Min Range: -18.6217
Max Act: 17.9967. Min Act: -0.1700
Data Index: 3842209 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.6217. Min Range: -18.6217
Max Act: 17.9967. Min Act: -0.1700
Data Index: 2756201 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.6217. Min Range: -18.6217
Max Act: 17.9967. Min Act: -0.1700
Data Index: 8751585 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.6217. Min Range: -18.6217
Max Act: 17.9967. Min Act: -0.1700
Data Index: 8727500 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.6217. Min Range: -18.6217
Max Act: 17.8717. Min Act: -0.1700
Data Index: 1429321 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.6217. Min Range: -18.6217
Max Act: 17.9967. Min Act: -0.1700
Data Index: 1576135 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.6217. Min Range: -18.6217
Max Act: 17.9967. Min Act: -0.1700
Data Index: 8407046 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.6217. Min Range: -18.6217
Max Act: 17.9967. Min Act: -0.1700
Data Index: 4353994 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19