Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1605 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.9444. Min Act: -0.1700
Data Index: 5090892 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.8818. Min Act: -0.1700
Data Index: 7648434 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.8506. Min Act: -0.1700
Data Index: 5807317 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.8506. Min Act: -0.1700
Data Index: 6730058 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.8037. Min Act: -0.1700
Data Index: 176781 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.7880. Min Act: -0.1700
Data Index: 2422537 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.7724. Min Act: -0.1700
Data Index: 7691272 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.7568. Min Act: -0.1700
Data Index: 7312508 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.7568. Min Act: -0.1700
Data Index: 8421671 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.7255. Min Act: -0.1700
Data Index: 2802084 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.7098. Min Act: -0.1700
Data Index: 7853690 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.6942. Min Act: -0.1700
Data Index: 4568857 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.6785. Min Act: -0.1700
Data Index: 4568880 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.6629. Min Act: -0.1700
Data Index: 4279895 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.6629. Min Act: -0.1700
Data Index: 8447253 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.6316. Min Act: -0.1700
Data Index: 4191641 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.6472. Min Act: -0.1700
Data Index: 8629262 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.6629. Min Act: -0.1700
Data Index: 3868752 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.6316. Min Act: -0.1700
Data Index: 5102017 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9444. Min Range: -3.9444
Max Act: 3.5533. Min Act: -0.1700
Data Index: 3125349 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19