Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2056 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.2582. Min Range: -2.2582
Max Act: 2.2582. Min Act: -0.0000
Data Index: 1164361 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2582. Min Range: -2.2582
Max Act: 2.2432. Min Act: -0.0000
Data Index: 1732982 (The Pile)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2582. Min Range: -2.2582
Max Act: 2.1240. Min Act: -0.0000
Data Index: 675187 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2582. Min Range: -2.2582
Max Act: 2.1804. Min Act: -0.0000
Data Index: 415424 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.9591. Min Act: -0.0000
Data Index: 1537309 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.8436. Min Act: -0.0000
Data Index: 672308 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2582. Min Range: -2.2582
Max Act: 2.2361. Min Act: -0.0000
Data Index: 1135218 (The Pile)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.9833. Min Act: -0.0000
Data Index: 1872201 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2582. Min Range: -2.2582
Max Act: 2.0802. Min Act: -0.0000
Data Index: 1930674 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2582. Min Range: -2.2582
Max Act: 2.1614. Min Act: -0.0000
Data Index: 418655 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2582. Min Range: -2.2582
Max Act: 2.1628. Min Act: -0.0000
Data Index: 76321 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.8333. Min Act: -0.0000
Data Index: 785236 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2582. Min Range: -2.2582
Max Act: 2.1646. Min Act: -0.0000
Data Index: 1729024 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.8750. Min Act: -0.0000
Data Index: 706611 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.8528. Min Act: -0.0000
Data Index: 1604813 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.9997. Min Act: -0.0000
Data Index: 789061 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.9435. Min Act: -0.0000
Data Index: 830830 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.8458. Min Act: -0.0000
Data Index: 1229920 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.9268. Min Act: -0.0000
Data Index: 856658 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2582. Min Range: -2.2582
Max Act: 1.8359. Min Act: -0.0000
Data Index: 1867480 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19