Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 544 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.2206. Min Act: -0.0004
Data Index: 472085 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.2075. Min Act: -0.0004
Data Index: 131323 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1999. Min Act: -0.0004
Data Index: 1487635 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.2022. Min Act: -0.0004
Data Index: 909670 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.2022. Min Act: -0.0004
Data Index: 1774411 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1959. Min Act: -0.0004
Data Index: 395067 (The Pile)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.2021. Min Act: -0.0005
Data Index: 224010 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.2005. Min Act: -0.0004
Data Index: 225442 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1941. Min Act: -0.0004
Data Index: 225395 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1923. Min Act: -0.0005
Data Index: 1200873 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1982. Min Act: -0.0004
Data Index: 1461605 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1916. Min Act: -0.0004
Data Index: 1078448 (The Pile)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1896. Min Act: -0.0004
Data Index: 1672127 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.2032. Min Act: -0.0004
Data Index: 1962231 (The Pile)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1960. Min Act: -0.0004
Data Index: 293481 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1886. Min Act: -0.0004
Data Index: 642307 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1890. Min Act: -0.0004
Data Index: 1045659 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1942. Min Act: -0.0004
Data Index: 1253420 (The Pile)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1873. Min Act: -0.0004
Data Index: 815469 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2206. Min Range: -0.2206
Max Act: 0.1941. Min Act: -0.0004
Data Index: 1466473 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19