Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2006 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2162. Min Range: -8.2162
Max Act: 8.2162. Min Act: -0.1700
Data Index: 3099362 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2162. Min Range: -8.2162
Max Act: 8.1537. Min Act: -0.1700
Data Index: 3453223 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2162. Min Range: -8.2162
Max Act: 8.1225. Min Act: -0.1700
Data Index: 8567571 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2162. Min Range: -8.2162
Max Act: 8.0600. Min Act: -0.1700
Data Index: 3794316 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2162. Min Range: -8.2162
Max Act: 8.0600. Min Act: -0.1700
Data Index: 2746203 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2162. Min Range: -8.2162
Max Act: 8.0600. Min Act: -0.1700
Data Index: 3099344 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9975. Min Act: -0.1700
Data Index: 8128940 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9975. Min Act: -0.1700
Data Index: 6207934 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9975. Min Act: -0.1700
Data Index: 8128926 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9662. Min Act: -0.1700
Data Index: 5153890 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9350. Min Act: -0.1700
Data Index: 715238 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9662. Min Act: -0.1700
Data Index: 6207945 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9662. Min Act: -0.1700
Data Index: 1370264 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9350. Min Act: -0.1700
Data Index: 2551486 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9350. Min Act: -0.1700
Data Index: 6209036 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9350. Min Act: -0.1700
Data Index: 5677349 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9350. Min Act: -0.1700
Data Index: 3249001 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9662. Min Act: -0.1700
Data Index: 2909241 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9350. Min Act: -0.1700
Data Index: 7911425 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2162. Min Range: -8.2162
Max Act: 7.9350. Min Act: -0.1700
Data Index: 5627458 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19