Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 9 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.5100. Min Act: -0.0001
Data Index: 154475 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.4793. Min Act: -0.0001
Data Index: 1868808 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.2795. Min Act: -0.0001
Data Index: 1547970 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.2630. Min Act: -0.0001
Data Index: 1359737 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1206. Min Act: -0.0001
Data Index: 235837 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1271. Min Act: -0.0001
Data Index: 1146633 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1411. Min Act: -0.0001
Data Index: 1308929 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1599. Min Act: -0.0001
Data Index: 110113 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1875. Min Act: -0.0001
Data Index: 1653771 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1512. Min Act: -0.0001
Data Index: 422720 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1947. Min Act: -0.0001
Data Index: 72390 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.0995. Min Act: -0.0001
Data Index: 353352 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1069. Min Act: -0.0001
Data Index: 504600 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1258. Min Act: -0.0001
Data Index: 1119299 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.0940. Min Act: -0.0001
Data Index: 562911 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5100. Min Range: -1.5100
Max Act: 0.9996. Min Act: -0.0001
Data Index: 234952 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5100. Min Range: -1.5100
Max Act: 0.9967. Min Act: -0.0001
Data Index: 440277 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.1151. Min Act: -0.0001
Data Index: 1486424 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5100. Min Range: -1.5100
Max Act: 0.8067. Min Act: -0.0001
Data Index: 1056777 (The Pile)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5100. Min Range: -1.5100
Max Act: 1.0537. Min Act: -0.0001
Data Index: 1963895 (The Pile)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19