Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1899 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2313. Min Act: -0.0001
Data Index: 458880 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2184. Min Act: -0.0001
Data Index: 368443 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2293. Min Act: -0.0001
Data Index: 1907599 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2213. Min Act: -0.0001
Data Index: 1516296 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2099. Min Act: -0.0001
Data Index: 773703 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2145. Min Act: -0.0001
Data Index: 525666 (The Pile)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2197. Min Act: -0.0001
Data Index: 706547 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2042. Min Act: -0.0001
Data Index: 1818482 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2047. Min Act: -0.0001
Data Index: 1879607 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2053. Min Act: -0.0001
Data Index: 1717218 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.1970. Min Act: -0.0001
Data Index: 1429046 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2015. Min Act: -0.0001
Data Index: 479658 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.1941. Min Act: -0.0001
Data Index: 17485 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2152. Min Act: -0.0001
Data Index: 1693233 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2097. Min Act: -0.0001
Data Index: 232772 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.1944. Min Act: -0.0001
Data Index: 1232057 (The Pile)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.1936. Min Act: -0.0001
Data Index: 198787 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.1922. Min Act: -0.0001
Data Index: 1937187 (The Pile)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.2040. Min Act: -0.0001
Data Index: 88065 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2313. Min Range: -0.2313
Max Act: 0.1991. Min Act: -0.0001
Data Index: 1014352 (The Pile)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19