Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2160 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.0782. Min Act: 0.0000
Data Index: 1923933 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.2371. Min Act: -0.0000
Data Index: 753313 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.2029. Min Act: 0.0000
Data Index: 470061 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.1821. Min Act: 0.0001
Data Index: 164370 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.1082. Min Act: -0.0000
Data Index: 1787410 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.1203. Min Act: -0.0000
Data Index: 196413 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.2248. Min Act: 0.0000
Data Index: 1814358 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.0633. Min Act: -0.0000
Data Index: 793030 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.1651. Min Act: -0.0000
Data Index: 1992762 (The Pile)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2371. Min Range: -2.2371
Max Act: 2.1137. Min Act: 0.0000
Data Index: 1424725 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.9923. Min Act: -0.0000
Data Index: 1823411 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.7417. Min Act: 0.0000
Data Index: 1031039 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.8195. Min Act: -0.0000
Data Index: 816178 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.7131. Min Act: -0.0000
Data Index: 903224 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.8813. Min Act: -0.0000
Data Index: 570295 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.7495. Min Act: 0.0000
Data Index: 1371533 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.5744. Min Act: -0.0000
Data Index: 1292234 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.7465. Min Act: 0.0000
Data Index: 684870 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.7275. Min Act: 0.0000
Data Index: 17222 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2371. Min Range: -2.2371
Max Act: 1.5278. Min Act: -0.0000
Data Index: 258741 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19