Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1900 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.5371. Min Act: -0.1700
Data Index: 4008326 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.5371. Min Act: -0.1700
Data Index: 554326 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.5059. Min Act: -0.1700
Data Index: 7535746 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.4434. Min Act: -0.1700
Data Index: 412709 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.4121. Min Act: -0.1700
Data Index: 6259666 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2871. Min Act: -0.1700
Data Index: 3390502 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.3184. Min Act: -0.1700
Data Index: 5281315 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2871. Min Act: -0.1700
Data Index: 3607007 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2871. Min Act: -0.1700
Data Index: 1747732 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2559. Min Act: -0.1700
Data Index: 4165166 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.3184. Min Act: -0.1700
Data Index: 7404502 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2559. Min Act: -0.1700
Data Index: 4816047 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2559. Min Act: -0.1700
Data Index: 8751205 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2559. Min Act: -0.1700
Data Index: 3916687 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2559. Min Act: -0.1700
Data Index: 502040 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2246. Min Act: -0.1700
Data Index: 245105 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2559. Min Act: -0.1700
Data Index: 1224172 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.1934. Min Act: -0.1700
Data Index: 7392582 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2246. Min Act: -0.1700
Data Index: 2548262 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5371. Min Range: -4.5371
Max Act: 4.2246. Min Act: -0.1700
Data Index: 143743 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19