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

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

Neuron 3454 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1533. Min Range: -3.1533

Max Act: 3.1533. Min Act: -0.0000

Data Index: 604520 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.7249. Min Act: -0.0000

Data Index: 655908 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.8097. Min Act: -0.0000

Data Index: 855625 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.5307. Min Act: -0.0000

Data Index: 962341 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.4455. Min Act: -0.0000

Data Index: 159367 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.1152. Min Act: -0.0000

Data Index: 1242821 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 3.1533. Min Range: -3.1533

Max Act: 1.9678. Min Act: -0.0000

Data Index: 666943 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.0717. Min Act: -0.0000

Data Index: 257859 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.2772. Min Act: -0.0000

Data Index: 550063 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.0454. Min Act: -0.0000

Data Index: 1125753 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.1216. Min Act: -0.0000

Data Index: 1179227 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 3.1533. Min Range: -3.1533

Max Act: 1.9462. Min Act: -0.0000

Data Index: 192729 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 3.1533. Min Range: -3.1533

Max Act: 1.9210. Min Act: -0.0000

Data Index: 145123 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 3.1533. Min Range: -3.1533

Max Act: 1.8156. Min Act: -0.0000

Data Index: 347497 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 3.1533. Min Range: -3.1533

Max Act: 2.0167. Min Act: -0.0000

Data Index: 711164 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.1533. Min Range: -3.1533

Max Act: 1.9596. Min Act: -0.0000

Data Index: 516004 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 3.1533. Min Range: -3.1533

Max Act: 1.8548. Min Act: -0.0000

Data Index: 388112 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 3.1533. Min Range: -3.1533

Max Act: 1.8240. Min Act: -0.0000

Data Index: 444312 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 3.1533. Min Range: -3.1533

Max Act: 1.9164. Min Act: -0.0000

Data Index: 840399 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 3.1533. Min Range: -3.1533

Max Act: 1.8686. Min Act: -0.0000

Data Index: 32937 (C4 (Web Text))

Max Activating Token Index: 327