Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2813 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4263. Min Range: -4.4263
Max Act: 4.4263. Min Act: -0.1700
Data Index: 8023655 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4263. Min Range: -4.4263
Max Act: 4.2700. Min Act: -0.1700
Data Index: 4991350 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4263. Min Range: -4.4263
Max Act: 4.1138. Min Act: -0.1700
Data Index: 7433146 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4263. Min Range: -4.4263
Max Act: 4.0825. Min Act: -0.1700
Data Index: 938258 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4263. Min Range: -4.4263
Max Act: 4.0512. Min Act: -0.1700
Data Index: 7356055 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.9575. Min Act: -0.1700
Data Index: 7644873 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4263. Min Range: -4.4263
Max Act: 4.0200. Min Act: -0.1700
Data Index: 7513804 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.9262. Min Act: -0.1700
Data Index: 2786492 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.8949. Min Act: -0.1700
Data Index: 5734386 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.8637. Min Act: -0.1700
Data Index: 7499592 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.8480. Min Act: -0.1700
Data Index: 3411847 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.8324. Min Act: -0.1700
Data Index: 539226 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.8011. Min Act: -0.1700
Data Index: 3377168 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.8011. Min Act: -0.1700
Data Index: 8226814 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.7855. Min Act: -0.1700
Data Index: 3990355 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.7542. Min Act: -0.1700
Data Index: 3562860 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.7855. Min Act: -0.1700
Data Index: 1786229 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.7855. Min Act: -0.1700
Data Index: 5494133 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.7699. Min Act: -0.1700
Data Index: 4660641 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4263. Min Range: -4.4263
Max Act: 3.7699. Min Act: -0.1700
Data Index: 8428875 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19