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

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

Neuron 384 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.8157. Min Act: -0.0000

Data Index: 43889 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.6674. Min Act: -0.0000

Data Index: 963939 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.7183. Min Act: -0.0000

Data Index: 501972 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.3448. Min Act: -0.0000

Data Index: 1183655 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.2327. Min Act: -0.0000

Data Index: 538426 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.3279. Min Act: -0.0000

Data Index: 329049 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.2539. Min Act: -0.0000

Data Index: 331614 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 3.8157. Min Range: -3.8157

Max Act: 3.0902. Min Act: -0.0000

Data Index: 50782 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.8600. Min Act: -0.0000

Data Index: 1004662 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.8320. Min Act: -0.0000

Data Index: 875368 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.8202. Min Act: -0.0000

Data Index: 612722 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.9332. Min Act: -0.0000

Data Index: 409583 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.7614. Min Act: -0.0000

Data Index: 42956 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.7567. Min Act: -0.0000

Data Index: 407189 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.6970. Min Act: -0.0000

Data Index: 389276 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.8386. Min Act: -0.0000

Data Index: 1203571 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.6740. Min Act: -0.0000

Data Index: 404351 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.6570. Min Act: -0.0000

Data Index: 1144651 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.6138. Min Act: -0.0000

Data Index: 696208 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 3.8157. Min Range: -3.8157

Max Act: 2.4579. Min Act: -0.0000

Data Index: 1341953 (C4 (Web Text))

Max Activating Token Index: 459