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

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

Neuron 3250 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3939. Min Act: -0.0003

Data Index: 880781 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3480. Min Act: -0.0002

Data Index: 58439 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3562. Min Act: -0.0003

Data Index: 346193 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3540. Min Act: -0.0002

Data Index: 549758 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3531. Min Act: -0.0003

Data Index: 774273 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3404. Min Act: -0.0003

Data Index: 793116 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3522. Min Act: -0.0003

Data Index: 219373 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3393. Min Act: -0.0002

Data Index: 1309645 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3317. Min Act: -0.0002

Data Index: 1285338 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3412. Min Act: -0.0003

Data Index: 316270 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3258. Min Act: -0.0002

Data Index: 846633 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3450. Min Act: -0.0002

Data Index: 1298689 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3441. Min Act: -0.0003

Data Index: 259259 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3317. Min Act: -0.0002

Data Index: 262867 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3306. Min Act: -0.0003

Data Index: 60250 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3290. Min Act: -0.0003

Data Index: 21619 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3150. Min Act: -0.0002

Data Index: 318480 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3244. Min Act: -0.0003

Data Index: 483931 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3244. Min Act: -0.0002

Data Index: 3424 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3345. Min Act: -0.0003

Data Index: 319759 (C4 (Web Text))

Max Activating Token Index: 845