Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4347. Min Range: -4.4347
Max Act: 4.4347. Min Act: -0.1700
Data Index: 373167 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4347. Min Range: -4.4347
Max Act: 4.2472. Min Act: -0.1700
Data Index: 8082482 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4347. Min Range: -4.4347
Max Act: 4.1534. Min Act: -0.1700
Data Index: 6509566 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4347. Min Range: -4.4347
Max Act: 4.1222. Min Act: -0.1700
Data Index: 1523882 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4347. Min Range: -4.4347
Max Act: 4.0596. Min Act: -0.1700
Data Index: 2646095 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4347. Min Range: -4.4347
Max Act: 4.0596. Min Act: -0.1700
Data Index: 4030827 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4347. Min Range: -4.4347
Max Act: 4.0284. Min Act: -0.1700
Data Index: 907434 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4347. Min Range: -4.4347
Max Act: 4.0284. Min Act: -0.1700
Data Index: 2362255 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9971. Min Act: -0.1700
Data Index: 2640476 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9971. Min Act: -0.1700
Data Index: 2647247 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9971. Min Act: -0.1700
Data Index: 6902372 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9971. Min Act: -0.1700
Data Index: 2929872 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9971. Min Act: -0.1700
Data Index: 6604958 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9971. Min Act: -0.1700
Data Index: 2699249 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9659. Min Act: -0.1700
Data Index: 6824439 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9659. Min Act: -0.1700
Data Index: 1093076 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9659. Min Act: -0.1700
Data Index: 8284584 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9346. Min Act: -0.1700
Data Index: 3579162 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9659. Min Act: -0.1700
Data Index: 992327 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4347. Min Range: -4.4347
Max Act: 3.9346. Min Act: -0.1700
Data Index: 3543639 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19