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

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

Neuron 2875 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3433. Min Act: -0.0002

Data Index: 699940 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2944. Min Act: -0.0002

Data Index: 1146652 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2817. Min Act: -0.0002

Data Index: 1236733 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2885. Min Act: -0.0002

Data Index: 120186 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2770. Min Act: -0.0002

Data Index: 1195652 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2946. Min Act: -0.0002

Data Index: 678068 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2730. Min Act: -0.0002

Data Index: 1166019 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2735. Min Act: -0.0002

Data Index: 407544 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2629. Min Act: -0.0002

Data Index: 425096 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2472. Min Act: -0.0002

Data Index: 522604 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2451. Min Act: -0.0002

Data Index: 462815 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2403. Min Act: -0.0001

Data Index: 589983 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2375. Min Act: -0.0002

Data Index: 330619 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2568. Min Act: -0.0002

Data Index: 635630 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2279. Min Act: -0.0002

Data Index: 111457 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2355. Min Act: -0.0002

Data Index: 321484 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2078. Min Act: -0.0002

Data Index: 809930 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2248. Min Act: -0.0002

Data Index: 7374 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2400. Min Act: -0.0001

Data Index: 746506 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2392. Min Act: -0.0001

Data Index: 298370 (C4 (Web Text))

Max Activating Token Index: 594