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

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

Neuron 3412 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.5244. Min Act: -0.0000

Data Index: 913412 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.5199. Min Act: -0.0000

Data Index: 795626 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.5350. Min Act: -0.0000

Data Index: 72560 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4335. Min Act: 0.0000

Data Index: 1257922 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4213. Min Act: -0.0000

Data Index: 82494 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4235. Min Act: 0.0000

Data Index: 426656 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4149. Min Act: -0.0000

Data Index: 113721 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1151031 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1083715 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4138. Min Act: -0.0000

Data Index: 676321 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1279493 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3673. Min Act: -0.0000

Data Index: 192043 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3680. Min Act: -0.0000

Data Index: 467870 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1055683 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3406. Min Act: -0.0000

Data Index: 374995 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3234. Min Act: -0.0000

Data Index: 395082 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1115319 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3126. Min Act: -0.0000

Data Index: 669371 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3240. Min Act: -0.0000

Data Index: 957337 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3117. Min Act: -0.0000

Data Index: 727883 (C4 (Web Text))

Max Activating Token Index: 846