Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3160 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.8452. Min Act: -0.0000
Data Index: 1160946 (The Pile)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.5409. Min Act: -0.0000
Data Index: 339291 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.5536. Min Act: -0.0000
Data Index: 573678 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.4958. Min Act: -0.0000
Data Index: 263962 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.4785. Min Act: -0.0000
Data Index: 811853 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.5930. Min Act: -0.0000
Data Index: 567653 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.4396. Min Act: -0.0000
Data Index: 777312 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.5842. Min Act: -0.0000
Data Index: 324084 (The Pile)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.5698. Min Act: -0.0000
Data Index: 247421 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.4094. Min Act: -0.0000
Data Index: 472204 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.3800. Min Act: -0.0000
Data Index: 1190307 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.3571. Min Act: -0.0000
Data Index: 611933 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.4984. Min Act: -0.0000
Data Index: 1592256 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.3839. Min Act: -0.0000
Data Index: 489647 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.2960. Min Act: -0.0000
Data Index: 1550974 (The Pile)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.4319. Min Act: -0.0000
Data Index: 504886 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.4229. Min Act: -0.0000
Data Index: 653643 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.4370. Min Act: -0.0000
Data Index: 42438 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.2808. Min Act: -0.0000
Data Index: 178086 (The Pile)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8452. Min Range: -1.8452
Max Act: 1.3197. Min Act: -0.0000
Data Index: 1705862 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19