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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 109 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.5918. Min Act: -0.0000

Data Index: 501366 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.5295. Min Act: -0.0000

Data Index: 371340 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.5610. Min Act: -0.0000

Data Index: 935701 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.4040. Min Act: -0.0000

Data Index: 114728 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.4319. Min Act: -0.0000

Data Index: 45128 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.4177. Min Act: -0.0000

Data Index: 933122 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3607. Min Act: -0.0000

Data Index: 388244 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1348890 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3691. Min Act: -0.0000

Data Index: 45270 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3534. Min Act: -0.0000

Data Index: 180669 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3534. Min Act: -0.0000

Data Index: 68178 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3625. Min Act: -0.0001

Data Index: 1042035 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1297177 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3508. Min Act: -0.0000

Data Index: 399216 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3350. Min Act: -0.0000

Data Index: 88530 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3334. Min Act: -0.0000

Data Index: 836720 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1146423 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3262. Min Act: -0.0000

Data Index: 746070 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.2932. Min Act: -0.0000

Data Index: 570671 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.5918. Min Range: -0.5918

Max Act: 0.3120. Min Act: -0.0001

Data Index: 437248 (C4 (Web Text))

Max Activating Token Index: 157