Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3217 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2304. Min Range: -3.2304

Max Act: 3.0130. Min Act: -0.0000

Data Index: 472534 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 3.2304. Min Range: -3.2304

Max Act: 3.0368. Min Act: -0.0000

Data Index: 694777 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.6525. Min Act: -0.0000

Data Index: 761616 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.7892. Min Act: -0.0000

Data Index: 401490 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 3.2304. Min Range: -3.2304

Max Act: 3.2304. Min Act: -0.0000

Data Index: 12457 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 3.2304. Min Range: -3.2304

Max Act: 3.1910. Min Act: -0.0000

Data Index: 1049402 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.4891. Min Act: -0.0000

Data Index: 1277883 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.6723. Min Act: -0.0000

Data Index: 1300593 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.8263. Min Act: -0.0000

Data Index: 1049788 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.4391. Min Act: -0.0000

Data Index: 737162 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.7885. Min Act: -0.0000

Data Index: 1248206 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.5811. Min Act: -0.0000

Data Index: 455255 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.6208. Min Act: -0.0000

Data Index: 838511 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.3235. Min Act: 0.0000

Data Index: 988294 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.3836. Min Act: -0.0000

Data Index: 1339169 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.3288. Min Act: -0.0000

Data Index: 1415639 (Python Code)

Max Activating Token Index: 766

Text #16

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.2661. Min Act: -0.0000

Data Index: 1299009 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.2238. Min Act: -0.0000

Data Index: 583951 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.2769. Min Act: -0.0000

Data Index: 689635 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 3.2304. Min Range: -3.2304

Max Act: 2.1431. Min Act: -0.0000

Data Index: 1064320 (C4 (Web Text))

Max Activating Token Index: 76