Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3432 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9615. Min Act: -0.0000

Data Index: 452319 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1262538 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9063. Min Act: -0.0001

Data Index: 716324 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.9170. Min Act: -0.0000

Data Index: 359847 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8484. Min Act: -0.0000

Data Index: 361444 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8259. Min Act: -0.0000

Data Index: 909177 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8208. Min Act: -0.0000

Data Index: 205753 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7966. Min Act: -0.0000

Data Index: 244375 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8227. Min Act: -0.0001

Data Index: 199879 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.8144. Min Act: -0.0001

Data Index: 272916 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7223. Min Act: -0.0000

Data Index: 730878 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7365. Min Act: -0.0000

Data Index: 857207 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7559. Min Act: -0.0000

Data Index: 889623 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7786. Min Act: -0.0000

Data Index: 39727 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7242. Min Act: -0.0000

Data Index: 395173 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7161. Min Act: -0.0000

Data Index: 389289 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7628. Min Act: -0.0001

Data Index: 1075387 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7579. Min Act: -0.0000

Data Index: 331847 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1316610 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7281. Min Act: -0.0000

Data Index: 544914 (C4 (Web Text))

Max Activating Token Index: 515