Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1319 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1330261 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7750. Min Act: -0.0000

Data Index: 127512 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1339822 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1692189 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7594. Min Act: -0.0000

Data Index: 345199 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1268462 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1478349 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6426. Min Act: -0.0000

Data Index: 955568 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7507. Min Act: -0.0000

Data Index: 468917 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7289. Min Act: -0.0000

Data Index: 393712 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6510. Min Act: -0.0000

Data Index: 630305 (The Pile)

Max Activating Token Index: 220

Text #11

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6444. Min Act: -0.0000

Data Index: 659285 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6399. Min Act: -0.0000

Data Index: 923986 (The Pile)

Max Activating Token Index: 780

Text #13

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6075. Min Act: -0.0000

Data Index: 895229 (The Pile)

Max Activating Token Index: 870

Text #14

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.5734. Min Act: -0.0000

Data Index: 725566 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1085428 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1176129 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1142194 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1145907 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1315185 (The Pile)

Max Activating Token Index: 450