Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5105 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2083. Min Range: -8.2083
Max Act: 8.2083. Min Act: -0.1700
Data Index: 4994735 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2083. Min Range: -8.2083
Max Act: 8.2083. Min Act: -0.1700
Data Index: 1008184 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2083. Min Range: -8.2083
Max Act: 8.1458. Min Act: -0.1700
Data Index: 8335367 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2083. Min Range: -8.2083
Max Act: 8.1458. Min Act: -0.1700
Data Index: 1779716 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2083. Min Range: -8.2083
Max Act: 8.1145. Min Act: -0.1700
Data Index: 6540822 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2083. Min Range: -8.2083
Max Act: 8.0833. Min Act: -0.1700
Data Index: 4352401 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2083. Min Range: -8.2083
Max Act: 8.0520. Min Act: -0.1700
Data Index: 1155288 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2083. Min Range: -8.2083
Max Act: 8.0208. Min Act: -0.1700
Data Index: 4095226 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2083. Min Range: -8.2083
Max Act: 8.0208. Min Act: -0.1700
Data Index: 2415940 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.9583. Min Act: -0.1700
Data Index: 4881033 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.9270. Min Act: -0.1700
Data Index: 4889089 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.8958. Min Act: -0.1700
Data Index: 6729606 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.8958. Min Act: -0.1700
Data Index: 4043364 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.8958. Min Act: -0.1700
Data Index: 4085198 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.8958. Min Act: -0.1700
Data Index: 8734482 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.8645. Min Act: -0.1700
Data Index: 4877045 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.8333. Min Act: -0.1700
Data Index: 2104903 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.8645. Min Act: -0.1700
Data Index: 5557359 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.8333. Min Act: -0.1700
Data Index: 8774833 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2083. Min Range: -8.2083
Max Act: 7.7708. Min Act: -0.1700
Data Index: 2538442 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19