Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 866 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2894. Min Act: -0.0004
Data Index: 581126 (The Pile)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2976. Min Act: -0.0004
Data Index: 1428244 (The Pile)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2900. Min Act: -0.0004
Data Index: 1479215 (The Pile)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2883. Min Act: -0.0004
Data Index: 398224 (The Pile)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2770. Min Act: -0.0004
Data Index: 597139 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2660. Min Act: -0.0004
Data Index: 721911 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2793. Min Act: -0.0004
Data Index: 793027 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2778. Min Act: -0.0004
Data Index: 1775519 (The Pile)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2587. Min Act: -0.0004
Data Index: 1628187 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2672. Min Act: -0.0004
Data Index: 726882 (The Pile)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2680. Min Act: -0.0004
Data Index: 913165 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2655. Min Act: -0.0004
Data Index: 1636573 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2740. Min Act: -0.0004
Data Index: 1487743 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2565. Min Act: -0.0004
Data Index: 122672 (The Pile)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2546. Min Act: -0.0004
Data Index: 1313976 (The Pile)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2626. Min Act: -0.0004
Data Index: 1195018 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2610. Min Act: -0.0004
Data Index: 195891 (The Pile)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2620. Min Act: -0.0004
Data Index: 1540047 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2627. Min Act: -0.0004
Data Index: 673433 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2976. Min Range: -0.2976
Max Act: 0.2534. Min Act: -0.0004
Data Index: 1929577 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19