Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1417 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.7965. Min Act: -0.0000
Data Index: 456677 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.7892. Min Act: -0.0000
Data Index: 1360175 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.3091. Min Act: -0.0000
Data Index: 1018485 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.2965. Min Act: 0.0000
Data Index: 1655972 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.2889. Min Act: 0.0000
Data Index: 1048079 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.2747. Min Act: -0.0000
Data Index: 1266123 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.1691. Min Act: -0.0000
Data Index: 26223 (The Pile)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.1314. Min Act: -0.0000
Data Index: 1964612 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.3565. Min Act: -0.0000
Data Index: 1034595 (The Pile)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.2735. Min Act: -0.0000
Data Index: 569982 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.1899. Min Act: -0.0000
Data Index: 1405420 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.2207. Min Act: -0.0001
Data Index: 477934 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.1252. Min Act: -0.0000
Data Index: 1505740 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.2239. Min Act: -0.0000
Data Index: 731188 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.1157. Min Act: -0.0000
Data Index: 57362 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7965. Min Range: -1.7965
Max Act: 0.9899. Min Act: -0.0000
Data Index: 1766535 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.1809. Min Act: 0.0000
Data Index: 1402892 (The Pile)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.0543. Min Act: -0.0000
Data Index: 802372 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7965. Min Range: -1.7965
Max Act: 0.8474. Min Act: -0.0000
Data Index: 1013242 (The Pile)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7965. Min Range: -1.7965
Max Act: 1.0142. Min Act: -0.0000
Data Index: 12857 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19