Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2186 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.3186. Min Act: -0.0001
Data Index: 781548 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.3511. Min Act: -0.0001
Data Index: 916846 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.3266. Min Act: -0.0001
Data Index: 788085 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.3037. Min Act: -0.0001
Data Index: 670404 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.3147. Min Act: -0.0001
Data Index: 1636111 (The Pile)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.3096. Min Act: -0.0001
Data Index: 1527204 (The Pile)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2822. Min Act: -0.0001
Data Index: 575881 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2769. Min Act: -0.0001
Data Index: 923595 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.3115. Min Act: -0.0001
Data Index: 1385439 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2724. Min Act: -0.0001
Data Index: 1358254 (The Pile)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2951. Min Act: -0.0001
Data Index: 448961 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2772. Min Act: -0.0001
Data Index: 265788 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2861. Min Act: -0.0001
Data Index: 232054 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2868. Min Act: -0.0001
Data Index: 1558845 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2839. Min Act: -0.0001
Data Index: 614435 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.3326. Min Act: -0.0001
Data Index: 1759812 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2875. Min Act: -0.0001
Data Index: 562360 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2893. Min Act: -0.0001
Data Index: 1309367 (The Pile)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2880. Min Act: -0.0001
Data Index: 540251 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3511. Min Range: -0.3511
Max Act: 0.2934. Min Act: -0.0001
Data Index: 1535202 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19