Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4713 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.6123. Min Act: -0.0000

Data Index: 892613 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1109069 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4263. Min Act: -0.0000

Data Index: 53019 (The Pile)

Max Activating Token Index: 443

Text #3

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1045379 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4092. Min Act: -0.0000

Data Index: 532956 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3767. Min Act: -0.0000

Data Index: 206380 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1077230 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1473456 (The Pile)

Max Activating Token Index: 438

Text #8

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3704. Min Act: -0.0000

Data Index: 647978 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3878. Min Act: -0.0000

Data Index: 211314 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1263449 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3619. Min Act: -0.0000

Data Index: 1452944 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.4234. Min Act: -0.0000

Data Index: 893860 (The Pile)

Max Activating Token Index: 801

Text #13

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3945. Min Act: -0.0000

Data Index: 956362 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1902202 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3190. Min Act: -0.0000

Data Index: 469706 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1217747 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3283. Min Act: -0.0000

Data Index: 72325 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3274. Min Act: -0.0000

Data Index: 325124 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 0.6123. Min Range: -0.6123

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1239504 (The Pile)

Max Activating Token Index: 944