Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.8511. Min Act: -0.1700
Data Index: 7404504 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.7886. Min Act: -0.1700
Data Index: 2786655 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.7886. Min Act: -0.1700
Data Index: 2801435 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.7886. Min Act: -0.1700
Data Index: 1441177 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.7261. Min Act: -0.1700
Data Index: 3013641 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.7573. Min Act: -0.1700
Data Index: 5981857 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.6948. Min Act: -0.1700
Data Index: 5114926 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.7261. Min Act: -0.1700
Data Index: 7568678 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.7261. Min Act: -0.1700
Data Index: 678326 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.6636. Min Act: -0.1700
Data Index: 329714 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.6323. Min Act: -0.1700
Data Index: 11153 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.6636. Min Act: -0.1700
Data Index: 2068618 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.6948. Min Act: -0.1700
Data Index: 1608163 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.6636. Min Act: -0.1700
Data Index: 8441499 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.6323. Min Act: -0.1700
Data Index: 1440098 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.6011. Min Act: -0.1700
Data Index: 4911221 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.6011. Min Act: -0.1700
Data Index: 8612359 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.5698. Min Act: -0.1700
Data Index: 181675 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.5386. Min Act: -0.1700
Data Index: 5568058 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8511. Min Range: -5.8511
Max Act: 5.5386. Min Act: -0.1700
Data Index: 6154680 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19