Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5117 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0248. Min Range: -5.0248
Max Act: 5.0248. Min Act: -0.1700
Data Index: 769005 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.8685. Min Act: -0.1700
Data Index: 2292243 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7748. Min Act: -0.1700
Data Index: 7309269 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7435. Min Act: -0.1700
Data Index: 97677 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7435. Min Act: -0.1700
Data Index: 597325 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6810. Min Act: -0.1700
Data Index: 8065135 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6498. Min Act: -0.1700
Data Index: 6931587 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6185. Min Act: -0.1700
Data Index: 6085200 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6498. Min Act: -0.1700
Data Index: 2661579 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6498. Min Act: -0.1700
Data Index: 1744879 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6185. Min Act: -0.1700
Data Index: 2632712 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6185. Min Act: -0.1700
Data Index: 6341055 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5873. Min Act: -0.1700
Data Index: 7887940 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6185. Min Act: -0.1700
Data Index: 4267677 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5560. Min Act: -0.1700
Data Index: 7825691 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5560. Min Act: -0.1700
Data Index: 5004844 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5560. Min Act: -0.1700
Data Index: 8626294 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5560. Min Act: -0.1700
Data Index: 7809900 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.5560. Min Act: -0.1700
Data Index: 1933406 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.4935. Min Act: -0.1700
Data Index: 4740235 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19