Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.9905. Min Act: -0.1700
Data Index: 441133 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.8967. Min Act: -0.1700
Data Index: 972036 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.8655. Min Act: -0.1700
Data Index: 5639436 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.8655. Min Act: -0.1700
Data Index: 3895825 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.8342. Min Act: -0.1700
Data Index: 3031025 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.8030. Min Act: -0.1700
Data Index: 6136574 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7717. Min Act: -0.1700
Data Index: 1383238 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7717. Min Act: -0.1700
Data Index: 1313229 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7717. Min Act: -0.1700
Data Index: 569385 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7717. Min Act: -0.1700
Data Index: 4018105 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7717. Min Act: -0.1700
Data Index: 1120284 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7405. Min Act: -0.1700
Data Index: 1440295 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7405. Min Act: -0.1700
Data Index: 4804695 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7092. Min Act: -0.1700
Data Index: 579919 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7405. Min Act: -0.1700
Data Index: 5852350 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7405. Min Act: -0.1700
Data Index: 4002341 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7405. Min Act: -0.1700
Data Index: 995022 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7405. Min Act: -0.1700
Data Index: 3016220 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7405. Min Act: -0.1700
Data Index: 1204925 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9905. Min Range: -5.9905
Max Act: 5.7405. Min Act: -0.1700
Data Index: 3801111 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19