Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 829 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.6255. Min Act: -0.0001
Data Index: 1807965 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.3081. Min Act: -0.0001
Data Index: 1631948 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.2047. Min Act: -0.0001
Data Index: 848094 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.2133. Min Act: -0.0001
Data Index: 853732 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.0367. Min Act: -0.0001
Data Index: 18759 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.1315. Min Act: -0.0001
Data Index: 923324 (The Pile)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.1406. Min Act: -0.0001
Data Index: 1459219 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6255. Min Range: -1.6255
Max Act: 0.9781. Min Act: -0.0001
Data Index: 330957 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.0229. Min Act: -0.0001
Data Index: 528470 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.2342. Min Act: -0.0001
Data Index: 1188269 (The Pile)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.0660. Min Act: -0.0001
Data Index: 1655250 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6255. Min Range: -1.6255
Max Act: 0.9748. Min Act: -0.0001
Data Index: 510516 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.1474. Min Act: -0.0001
Data Index: 201795 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.1509. Min Act: -0.0001
Data Index: 1344272 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6255. Min Range: -1.6255
Max Act: 0.9563. Min Act: -0.0001
Data Index: 662151 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6255. Min Range: -1.6255
Max Act: 0.9805. Min Act: -0.0001
Data Index: 1544099 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.0872. Min Act: -0.0001
Data Index: 1561636 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6255. Min Range: -1.6255
Max Act: 1.0159. Min Act: -0.0001
Data Index: 1977909 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6255. Min Range: -1.6255
Max Act: 0.9446. Min Act: -0.0001
Data Index: 100541 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6255. Min Range: -1.6255
Max Act: 0.9881. Min Act: -0.0001
Data Index: 35707 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19