Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2880 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3121. Min Range: -7.3121
Max Act: 7.3121. Min Act: -0.1700
Data Index: 5172251 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3121. Min Range: -7.3121
Max Act: 7.1246. Min Act: -0.1700
Data Index: 5143247 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3121. Min Range: -7.3121
Max Act: 7.0933. Min Act: -0.1700
Data Index: 2104499 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3121. Min Range: -7.3121
Max Act: 7.0933. Min Act: -0.1700
Data Index: 6540764 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3121. Min Range: -7.3121
Max Act: 7.0308. Min Act: -0.1700
Data Index: 7815795 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9683. Min Act: -0.1700
Data Index: 2081869 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9996. Min Act: -0.1700
Data Index: 2282711 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9996. Min Act: -0.1700
Data Index: 7994673 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9996. Min Act: -0.1700
Data Index: 7988851 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9371. Min Act: -0.1700
Data Index: 3981698 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9371. Min Act: -0.1700
Data Index: 471968 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9371. Min Act: -0.1700
Data Index: 8224736 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9371. Min Act: -0.1700
Data Index: 4304429 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9371. Min Act: -0.1700
Data Index: 7688827 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9058. Min Act: -0.1700
Data Index: 1958272 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9371. Min Act: -0.1700
Data Index: 4621773 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.8746. Min Act: -0.1700
Data Index: 4777725 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9058. Min Act: -0.1700
Data Index: 6779404 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.8746. Min Act: -0.1700
Data Index: 1498718 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3121. Min Range: -7.3121
Max Act: 6.9058. Min Act: -0.1700
Data Index: 6623438 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19