Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2713 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.6402. Min Act: -0.1700
Data Index: 2194800 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.5777. Min Act: -0.1700
Data Index: 3660650 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.5464. Min Act: -0.1700
Data Index: 4532166 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.5152. Min Act: -0.1700
Data Index: 4425522 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.5152. Min Act: -0.1700
Data Index: 7336808 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.5152. Min Act: -0.1700
Data Index: 3958914 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.4527. Min Act: -0.1700
Data Index: 7153143 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.4527. Min Act: -0.1700
Data Index: 7434767 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.4214. Min Act: -0.1700
Data Index: 3117547 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.4214. Min Act: -0.1700
Data Index: 6256291 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.4214. Min Act: -0.1700
Data Index: 3643688 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.3902. Min Act: -0.1700
Data Index: 6188413 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.4214. Min Act: -0.1700
Data Index: 4415305 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.3902. Min Act: -0.1700
Data Index: 1572575 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.3277. Min Act: -0.1700
Data Index: 5278151 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.2964. Min Act: -0.1700
Data Index: 6413876 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.3589. Min Act: -0.1700
Data Index: 4779975 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.2964. Min Act: -0.1700
Data Index: 5158899 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.2964. Min Act: -0.1700
Data Index: 4914310 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6402. Min Range: -6.6402
Max Act: 6.2964. Min Act: -0.1700
Data Index: 6496283 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19