Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3553. Min Range: -4.3553
Max Act: 4.3553. Min Act: -0.1700
Data Index: 3801312 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.9802. Min Act: -0.1700
Data Index: 7512878 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.8551. Min Act: -0.1700
Data Index: 7272683 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.8239. Min Act: -0.1700
Data Index: 2337149 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.7926. Min Act: -0.1700
Data Index: 681232 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.7770. Min Act: -0.1700
Data Index: 4674839 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.7613. Min Act: -0.1700
Data Index: 716679 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.7300. Min Act: -0.1700
Data Index: 931218 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.7144. Min Act: -0.1700
Data Index: 3408739 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.7144. Min Act: -0.1700
Data Index: 2494455 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.6831. Min Act: -0.1700
Data Index: 860985 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.6831. Min Act: -0.1700
Data Index: 4966319 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.6988. Min Act: -0.1700
Data Index: 7386347 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.6675. Min Act: -0.1700
Data Index: 2526857 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.6831. Min Act: -0.1700
Data Index: 988589 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.6518. Min Act: -0.1700
Data Index: 8768531 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.6518. Min Act: -0.1700
Data Index: 253176 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.6518. Min Act: -0.1700
Data Index: 1071307 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.6205. Min Act: -0.1700
Data Index: 8123444 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3553. Min Range: -4.3553
Max Act: 3.5892. Min Act: -0.1700
Data Index: 165834 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19