Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3703 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1569. Min Range: -6.1569
Max Act: 6.1569. Min Act: -0.1700
Data Index: 6048320 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1569. Min Range: -6.1569
Max Act: 6.0006. Min Act: -0.1700
Data Index: 1986829 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1569. Min Range: -6.1569
Max Act: 6.0006. Min Act: -0.1700
Data Index: 2446849 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.9069. Min Act: -0.1700
Data Index: 3820184 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.9381. Min Act: -0.1700
Data Index: 4175641 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.9069. Min Act: -0.1700
Data Index: 8204431 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.9069. Min Act: -0.1700
Data Index: 564872 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.8756. Min Act: -0.1700
Data Index: 7362879 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.8756. Min Act: -0.1700
Data Index: 3135153 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.8756. Min Act: -0.1700
Data Index: 1417896 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.8444. Min Act: -0.1700
Data Index: 1490882 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.8444. Min Act: -0.1700
Data Index: 1687600 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.8131. Min Act: -0.1700
Data Index: 6359819 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.8131. Min Act: -0.1700
Data Index: 6863231 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.7819. Min Act: -0.1700
Data Index: 2202275 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.7819. Min Act: -0.1700
Data Index: 1248427 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.7819. Min Act: -0.1700
Data Index: 5514581 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.7819. Min Act: -0.1700
Data Index: 4461128 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.7819. Min Act: -0.1700
Data Index: 6013234 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1569. Min Range: -6.1569
Max Act: 5.7819. Min Act: -0.1700
Data Index: 1559749 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19