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

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

Neuron 3868 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.3365. Min Act: -0.0000

Data Index: 551723 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2897. Min Act: -0.0000

Data Index: 141424 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2904. Min Act: -0.0000

Data Index: 889935 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1202536 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2742. Min Act: -0.0000

Data Index: 424336 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2880. Min Act: -0.0000

Data Index: 328869 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2627. Min Act: -0.0000

Data Index: 147787 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2650. Min Act: -0.0000

Data Index: 925464 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2817. Min Act: -0.0000

Data Index: 252219 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2422. Min Act: -0.0000

Data Index: 339240 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1076773 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2543. Min Act: -0.0000

Data Index: 705116 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2263. Min Act: -0.0000

Data Index: 651088 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2318. Min Act: -0.0000

Data Index: 710405 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2384. Min Act: -0.0000

Data Index: 630838 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1175291 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2170. Min Act: -0.0000

Data Index: 598300 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2239. Min Act: -0.0000

Data Index: 172094 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1150062 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1143032 (C4 (Web Text))

Max Activating Token Index: 816