Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3928 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.9983. Min Act: -0.1700
Data Index: 1726709 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.9045. Min Act: -0.1700
Data Index: 5341364 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.8732. Min Act: -0.1700
Data Index: 3221731 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.8420. Min Act: -0.1700
Data Index: 7578086 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7481. Min Act: -0.1700
Data Index: 5361528 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7794. Min Act: -0.1700
Data Index: 239679 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7481. Min Act: -0.1700
Data Index: 8396657 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7481. Min Act: -0.1700
Data Index: 2905534 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7794. Min Act: -0.1700
Data Index: 186700 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7481. Min Act: -0.1700
Data Index: 5668875 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7169. Min Act: -0.1700
Data Index: 4961816 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7169. Min Act: -0.1700
Data Index: 6988364 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7169. Min Act: -0.1700
Data Index: 478979 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.7169. Min Act: -0.1700
Data Index: 3489038 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.6856. Min Act: -0.1700
Data Index: 1357358 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.6856. Min Act: -0.1700
Data Index: 3065525 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.6856. Min Act: -0.1700
Data Index: 3760613 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.6856. Min Act: -0.1700
Data Index: 2509970 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.6856. Min Act: -0.1700
Data Index: 7356945 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9983. Min Range: -3.9983
Max Act: 3.6543. Min Act: -0.1700
Data Index: 6225893 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19