Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1766 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.8310. Min Act: -0.0000
Data Index: 798786 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.7463. Min Act: -0.0000
Data Index: 713870 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.6830. Min Act: -0.0000
Data Index: 1736534 (The Pile)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.5067. Min Act: 0.0000
Data Index: 394071 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.3324. Min Act: 0.0000
Data Index: 1831547 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.2699. Min Act: -0.0000
Data Index: 660325 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.2365. Min Act: -0.0000
Data Index: 1779669 (The Pile)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.1944. Min Act: 0.0000
Data Index: 177432 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.2126. Min Act: -0.0000
Data Index: 655644 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.1751. Min Act: -0.0000
Data Index: 935625 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.2468. Min Act: 0.0000
Data Index: 1921148 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.1993. Min Act: 0.0000
Data Index: 94647 (The Pile)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.1632. Min Act: -0.0000
Data Index: 389202 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.1354. Min Act: -0.0000
Data Index: 1640777 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.0808. Min Act: -0.0000
Data Index: 1944209 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.0966. Min Act: -0.0000
Data Index: 810221 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.0588. Min Act: -0.0000
Data Index: 773419 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.1009. Min Act: -0.0000
Data Index: 1441597 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.0741. Min Act: -0.0000
Data Index: 112621 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8310. Min Range: -1.8310
Max Act: 1.0544. Min Act: -0.0000
Data Index: 279072 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19