Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 485 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.2198. Min Act: -0.0001
Data Index: 251446 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.2444. Min Act: -0.0001
Data Index: 62760 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1980. Min Act: -0.0001
Data Index: 1275363 (The Pile)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.2124. Min Act: -0.0001
Data Index: 732391 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.2416. Min Act: -0.0001
Data Index: 368349 (The Pile)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1972. Min Act: -0.0001
Data Index: 146130 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.2062. Min Act: -0.0001
Data Index: 206832 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1944. Min Act: -0.0001
Data Index: 1979271 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.2124. Min Act: -0.0001
Data Index: 272274 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1923. Min Act: -0.0001
Data Index: 1253353 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1856. Min Act: -0.0001
Data Index: 456748 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1653. Min Act: -0.0001
Data Index: 554156 (The Pile)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1907. Min Act: -0.0001
Data Index: 1194025 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1936. Min Act: -0.0001
Data Index: 574899 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1857. Min Act: -0.0001
Data Index: 22602 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1907. Min Act: -0.0001
Data Index: 1668312 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.2034. Min Act: -0.0001
Data Index: 1334722 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1886. Min Act: -0.0001
Data Index: 1126490 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1697. Min Act: -0.0001
Data Index: 295377 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2444. Min Range: -0.2444
Max Act: 0.1702. Min Act: -0.0001
Data Index: 1001244 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19