Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3055 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.7501. Min Range: -2.7501
Max Act: 2.7501. Min Act: -0.0000
Data Index: 1653425 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7501. Min Range: -2.7501
Max Act: 2.4547. Min Act: -0.0000
Data Index: 679941 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.7696. Min Act: -0.0000
Data Index: 480432 (The Pile)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.7224. Min Act: -0.0000
Data Index: 902479 (The Pile)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.4765. Min Act: -0.0000
Data Index: 1531329 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.2213. Min Act: -0.0000
Data Index: 1965358 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.6087. Min Act: -0.0000
Data Index: 581138 (The Pile)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.5218. Min Act: -0.0000
Data Index: 859264 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.2515. Min Act: -0.0000
Data Index: 1234625 (The Pile)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.4396. Min Act: -0.0000
Data Index: 666737 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.4094. Min Act: -0.0000
Data Index: 1590065 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.3582. Min Act: -0.0000
Data Index: 1245434 (The Pile)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.3347. Min Act: -0.0000
Data Index: 698287 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.4058. Min Act: -0.0000
Data Index: 1194533 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.3258. Min Act: -0.0000
Data Index: 1857852 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.2382. Min Act: -0.0000
Data Index: 304834 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.1038. Min Act: -0.0000
Data Index: 612603 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.2174. Min Act: -0.0000
Data Index: 611083 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.3049. Min Act: -0.0000
Data Index: 720076 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7501. Min Range: -2.7501
Max Act: 1.0936. Min Act: -0.0000
Data Index: 851252 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19