Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.9322. Min Act: -0.1700
Data Index: 4885909 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.8072. Min Act: -0.1700
Data Index: 1543108 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.7447. Min Act: -0.1700
Data Index: 3941912 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.7134. Min Act: -0.1700
Data Index: 4326707 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.6822. Min Act: -0.1700
Data Index: 6206816 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.6509. Min Act: -0.1700
Data Index: 1242946 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.6197. Min Act: -0.1700
Data Index: 7975209 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.6197. Min Act: -0.1700
Data Index: 742585 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.6509. Min Act: -0.1700
Data Index: 1867772 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.5884. Min Act: -0.1700
Data Index: 7171196 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.6509. Min Act: -0.1700
Data Index: 3687250 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.5884. Min Act: -0.1700
Data Index: 2103797 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.5572. Min Act: -0.1700
Data Index: 4855315 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.5259. Min Act: -0.1700
Data Index: 3431258 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.5572. Min Act: -0.1700
Data Index: 3889705 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.4947. Min Act: -0.1700
Data Index: 7151297 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.5259. Min Act: -0.1700
Data Index: 975920 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.5259. Min Act: -0.1700
Data Index: 7053376 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.4947. Min Act: -0.1700
Data Index: 6628258 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9322. Min Range: -4.9322
Max Act: 4.5572. Min Act: -0.1700
Data Index: 7904134 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19