Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2286 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.9006. Min Act: -0.1700
Data Index: 1634951 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8693. Min Act: -0.1700
Data Index: 163665 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8693. Min Act: -0.1700
Data Index: 719194 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8693. Min Act: -0.1700
Data Index: 3533927 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 5292117 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 2624571 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 1087558 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 333396 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8068. Min Act: -0.1700
Data Index: 8650315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 8530626 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 6130554 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 1947505 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 1509030 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 4608843 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 3857240 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 3762534 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 176758 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8381. Min Act: -0.1700
Data Index: 3184542 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8068. Min Act: -0.1700
Data Index: 8458 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9006. Min Range: -3.9006
Max Act: 3.8068. Min Act: -0.1700
Data Index: 2574321 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19