Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 4049 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.4230. Min Act: -0.0001
Data Index: 702188 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.3421. Min Act: -0.0001
Data Index: 775728 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.3380. Min Act: -0.0001
Data Index: 985868 (The Pile)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.3149. Min Act: -0.0001
Data Index: 220771 (The Pile)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2757. Min Act: -0.0001
Data Index: 629604 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.3019. Min Act: -0.0001
Data Index: 1807304 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.3724. Min Act: -0.0001
Data Index: 1395478 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.0321. Min Act: -0.0001
Data Index: 927708 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2810. Min Act: -0.0001
Data Index: 330222 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2823. Min Act: -0.0001
Data Index: 1839360 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2789. Min Act: -0.0001
Data Index: 1953454 (The Pile)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2282. Min Act: -0.0001
Data Index: 952371 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2706. Min Act: -0.0001
Data Index: 1291740 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2873. Min Act: -0.0001
Data Index: 184527 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2030. Min Act: -0.0001
Data Index: 1963180 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2419. Min Act: -0.0001
Data Index: 160410 (The Pile)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.2267. Min Act: -0.0001
Data Index: 78621 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.3343. Min Act: -0.0001
Data Index: 1928275 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.1862. Min Act: -0.0001
Data Index: 1985615 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4230. Min Range: -1.4230
Max Act: 1.1987. Min Act: -0.0001
Data Index: 522497 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19