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

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

Neuron 569 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6618. Min Range: -3.6618

Max Act: 3.6618. Min Act: -0.0001

Data Index: 504226 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 3.6618. Min Range: -3.6618

Max Act: 3.6154. Min Act: -0.0001

Data Index: 1155450 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 3.6618. Min Range: -3.6618

Max Act: 3.6526. Min Act: -0.0001

Data Index: 878910 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.6618. Min Range: -3.6618

Max Act: 3.3888. Min Act: -0.0001

Data Index: 1187379 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 3.6618. Min Range: -3.6618

Max Act: 3.1438. Min Act: -0.0001

Data Index: 900277 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 3.6618. Min Range: -3.6618

Max Act: 3.2651. Min Act: -0.0001

Data Index: 1234294 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.8973. Min Act: -0.0001

Data Index: 605681 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 3.6618. Min Range: -3.6618

Max Act: 3.0920. Min Act: -0.0001

Data Index: 362982 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.9386. Min Act: -0.0001

Data Index: 1310111 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.8995. Min Act: -0.0001

Data Index: 436404 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.6907. Min Act: -0.0001

Data Index: 243336 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.6407. Min Act: -0.0001

Data Index: 1355329 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.6099. Min Act: -0.0001

Data Index: 1276467 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.3467. Min Act: -0.0001

Data Index: 306289 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.4102. Min Act: -0.0001

Data Index: 219976 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.7111. Min Act: -0.0001

Data Index: 500478 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.4501. Min Act: -0.0001

Data Index: 358758 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.2681. Min Act: -0.0001

Data Index: 192198 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.2562. Min Act: -0.0001

Data Index: 724410 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 3.6618. Min Range: -3.6618

Max Act: 2.2697. Min Act: -0.0001

Data Index: 909234 (C4 (Web Text))

Max Activating Token Index: 589