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

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

Neuron 1949 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0395. Min Range: -6.0395

Max Act: 6.0395. Min Act: -0.0000

Data Index: 830872 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 6.0395. Min Range: -6.0395

Max Act: 4.3757. Min Act: -0.0000

Data Index: 1269130 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 6.0395. Min Range: -6.0395

Max Act: 4.4215. Min Act: -0.0000

Data Index: 303184 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 6.0395. Min Range: -6.0395

Max Act: 4.3424. Min Act: -0.0000

Data Index: 161439 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 6.0395. Min Range: -6.0395

Max Act: 4.1670. Min Act: -0.0000

Data Index: 1237473 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.5328. Min Act: -0.0000

Data Index: 996544 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.2069. Min Act: -0.0000

Data Index: 583572 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.4685. Min Act: -0.0000

Data Index: 1275999 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.2985. Min Act: -0.0000

Data Index: 656258 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.3862. Min Act: -0.0000

Data Index: 692413 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.2235. Min Act: -0.0000

Data Index: 287479 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.2152. Min Act: -0.0000

Data Index: 847945 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.4920. Min Act: -0.0000

Data Index: 911009 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.2937. Min Act: -0.0000

Data Index: 619752 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.2524. Min Act: -0.0000

Data Index: 958694 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.0931. Min Act: -0.0000

Data Index: 591975 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.3759. Min Act: -0.0000

Data Index: 1224734 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.1894. Min Act: -0.0000

Data Index: 437692 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.0120. Min Act: -0.0000

Data Index: 808468 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 6.0395. Min Range: -6.0395

Max Act: 3.1373. Min Act: -0.0000

Data Index: 979143 (C4 (Web Text))

Max Activating Token Index: 109