Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2681 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.5632. Min Act: -0.1700
Data Index: 1876957 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.3757. Min Act: -0.1700
Data Index: 6026617 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.3445. Min Act: -0.1700
Data Index: 5440965 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.3445. Min Act: -0.1700
Data Index: 8667033 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.3132. Min Act: -0.1700
Data Index: 6161953 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.3132. Min Act: -0.1700
Data Index: 8572112 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.3132. Min Act: -0.1700
Data Index: 7923374 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.3132. Min Act: -0.1700
Data Index: 2362753 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2820. Min Act: -0.1700
Data Index: 7095646 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2820. Min Act: -0.1700
Data Index: 5981432 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2820. Min Act: -0.1700
Data Index: 4315491 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2820. Min Act: -0.1700
Data Index: 4475131 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2507. Min Act: -0.1700
Data Index: 5808063 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2195. Min Act: -0.1700
Data Index: 260701 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2195. Min Act: -0.1700
Data Index: 8391061 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2195. Min Act: -0.1700
Data Index: 4599135 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2195. Min Act: -0.1700
Data Index: 3464430 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2195. Min Act: -0.1700
Data Index: 1573408 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2195. Min Act: -0.1700
Data Index: 5929735 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5632. Min Range: -5.5632
Max Act: 5.2195. Min Act: -0.1700
Data Index: 4184351 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19