Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1666 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.7429. Min Act: -0.0000
Data Index: 785186 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.5566. Min Act: -0.0000
Data Index: 699603 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.5611. Min Act: -0.0000
Data Index: 294006 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.5515. Min Act: -0.0000
Data Index: 421669 (The Pile)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.4870. Min Act: -0.0000
Data Index: 465609 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.3773. Min Act: -0.0000
Data Index: 515315 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.4969. Min Act: -0.0000
Data Index: 190482 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.4110. Min Act: -0.0000
Data Index: 1444590 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.4110. Min Act: -0.0000
Data Index: 1967326 (The Pile)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.3666. Min Act: -0.0000
Data Index: 1454308 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.3003. Min Act: -0.0000
Data Index: 777093 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.3233. Min Act: -0.0000
Data Index: 657874 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.3920. Min Act: -0.0000
Data Index: 1967851 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.2288. Min Act: -0.0000
Data Index: 1383929 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.3640. Min Act: -0.0000
Data Index: 1564499 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.2792. Min Act: -0.0000
Data Index: 842637 (The Pile)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.3703. Min Act: -0.0000
Data Index: 154996 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.2218. Min Act: -0.0000
Data Index: 1756194 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.2468. Min Act: -0.0000
Data Index: 824933 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7429. Min Range: -1.7429
Max Act: 1.2583. Min Act: -0.0000
Data Index: 744897 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19