Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2456 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 3.4719. Min Range: -3.4719
Max Act: 3.4719. Min Act: -0.0000
Data Index: 1699830 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4719. Min Range: -3.4719
Max Act: 3.4096. Min Act: -0.0000
Data Index: 1333900 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4719. Min Range: -3.4719
Max Act: 3.4206. Min Act: -0.0000
Data Index: 1489887 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4719. Min Range: -3.4719
Max Act: 3.0226. Min Act: -0.0000
Data Index: 1818417 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.9801. Min Act: -0.0000
Data Index: 121335 (The Pile)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.9342. Min Act: -0.0000
Data Index: 710914 (The Pile)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.9990. Min Act: -0.0000
Data Index: 1843302 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.9545. Min Act: -0.0000
Data Index: 316472 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.9141. Min Act: -0.0000
Data Index: 1692277 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4719. Min Range: -3.4719
Max Act: 3.0329. Min Act: -0.0000
Data Index: 1839101 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.8668. Min Act: -0.0000
Data Index: 704170 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4719. Min Range: -3.4719
Max Act: 3.0089. Min Act: -0.0000
Data Index: 946529 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.8160. Min Act: -0.0000
Data Index: 433131 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.5865. Min Act: 0.0000
Data Index: 541876 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.6789. Min Act: -0.0000
Data Index: 1704645 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.5330. Min Act: -0.0000
Data Index: 990201 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.6377. Min Act: -0.0000
Data Index: 1733458 (The Pile)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4719. Min Range: -3.4719
Max Act: 3.0872. Min Act: -0.0000
Data Index: 18170 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.8079. Min Act: -0.0000
Data Index: 466481 (The Pile)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4719. Min Range: -3.4719
Max Act: 2.7628. Min Act: -0.0000
Data Index: 1137002 (The Pile)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19