Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 887 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8234. Min Range: -2.8234
Max Act: 2.8234. Min Act: -0.0001
Data Index: 564115 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8234. Min Range: -2.8234
Max Act: 2.5021. Min Act: -0.0001
Data Index: 849239 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8234. Min Range: -2.8234
Max Act: 2.3599. Min Act: -0.0001
Data Index: 455333 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8234. Min Range: -2.8234
Max Act: 2.2226. Min Act: -0.0001
Data Index: 573427 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8234. Min Range: -2.8234
Max Act: 2.4070. Min Act: -0.0001
Data Index: 88499 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8234. Min Range: -2.8234
Max Act: 2.1364. Min Act: -0.0001
Data Index: 186058 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8234. Min Range: -2.8234
Max Act: 2.0028. Min Act: -0.0001
Data Index: 870631 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.9476. Min Act: -0.0001
Data Index: 652785 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8234. Min Range: -2.8234
Max Act: 2.2375. Min Act: -0.0001
Data Index: 601897 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.7877. Min Act: -0.0001
Data Index: 384713 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.7976. Min Act: -0.0001
Data Index: 822730 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.8815. Min Act: -0.0001
Data Index: 517799 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.7667. Min Act: -0.0001
Data Index: 134696 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.5747. Min Act: -0.0001
Data Index: 1217169 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.5975. Min Act: -0.0001
Data Index: 667473 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.6305. Min Act: -0.0000
Data Index: 1477639 (Python Code)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.4403. Min Act: -0.0001
Data Index: 1195656 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.4950. Min Act: -0.0001
Data Index: 436945 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.3348. Min Act: -0.0001
Data Index: 88998 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8234. Min Range: -2.8234
Max Act: 1.4857. Min Act: -0.0001
Data Index: 1396206 (Python Code)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19