Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1359 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.5559. Min Act: -0.1700
Data Index: 7479376 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3684. Min Act: -0.1700
Data Index: 8143335 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.4309. Min Act: -0.1700
Data Index: 5021360 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.4309. Min Act: -0.1700
Data Index: 4828067 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.4309. Min Act: -0.1697
Data Index: 2963957 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.4309. Min Act: -0.1700
Data Index: 1404789 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.4309. Min Act: -0.1700
Data Index: 2180994 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3684. Min Act: -0.1700
Data Index: 3743716 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3684. Min Act: -0.1700
Data Index: 2132038 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3059. Min Act: -0.1697
Data Index: 1795979 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3059. Min Act: -0.1700
Data Index: 2226706 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3059. Min Act: -0.1699
Data Index: 7622802 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3059. Min Act: -0.1700
Data Index: 3003703 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3059. Min Act: -0.1700
Data Index: 2134959 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3059. Min Act: -0.1700
Data Index: 906142 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.2434. Min Act: -0.1700
Data Index: 3645133 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.2434. Min Act: -0.1700
Data Index: 4191551 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.3059. Min Act: -0.1700
Data Index: 8087058 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.1809. Min Act: -0.1700
Data Index: 3159015 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5559. Min Range: -7.5559
Max Act: 7.2434. Min Act: -0.1700
Data Index: 5093273 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19