Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3928 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.4772. Min Act: -0.1700
Data Index: 4147894 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.1022. Min Act: -0.1700
Data Index: 7042362 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.0709. Min Act: -0.1700
Data Index: 2967527 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.0709. Min Act: -0.1700
Data Index: 1927708 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.0084. Min Act: -0.1700
Data Index: 6938187 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.0084. Min Act: -0.1700
Data Index: 346563 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9771. Min Act: -0.1700
Data Index: 7037910 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4772. Min Range: -4.4772
Max Act: 4.0084. Min Act: -0.1700
Data Index: 5064861 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9459. Min Act: -0.1700
Data Index: 7390148 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9459. Min Act: -0.1700
Data Index: 4544510 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9459. Min Act: -0.1700
Data Index: 7448843 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9459. Min Act: -0.1700
Data Index: 4457572 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9459. Min Act: -0.1700
Data Index: 5981313 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9459. Min Act: -0.1700
Data Index: 3693893 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9459. Min Act: -0.1700
Data Index: 8538166 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9459. Min Act: -0.1700
Data Index: 4740215 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9146. Min Act: -0.1700
Data Index: 4290328 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9146. Min Act: -0.1700
Data Index: 1416520 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9146. Min Act: -0.1700
Data Index: 2969709 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4772. Min Range: -4.4772
Max Act: 3.9146. Min Act: -0.1700
Data Index: 7380311 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19