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

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

Neuron 5250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.9044. Min Act: -0.0000

Data Index: 846832 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.9211. Min Act: -0.0000

Data Index: 1236130 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 5.0933. Min Range: -5.0933

Max Act: 5.0933. Min Act: -0.0000

Data Index: 61150 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.8796. Min Act: -0.0000

Data Index: 903903 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.2410. Min Act: -0.0001

Data Index: 1335310 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.3476. Min Act: -0.0001

Data Index: 17435 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.4806. Min Act: -0.0001

Data Index: 930860 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.1248. Min Act: -0.0000

Data Index: 676571 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.2296. Min Act: -0.0000

Data Index: 7548 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.4301. Min Act: -0.0001

Data Index: 645818 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.5588. Min Act: -0.0000

Data Index: 1339471 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.5387. Min Act: -0.0000

Data Index: 166414 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.3787. Min Act: -0.0000

Data Index: 1158994 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.3329. Min Act: -0.0000

Data Index: 798149 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.1427. Min Act: -0.0000

Data Index: 90571 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.7266. Min Act: -0.0001

Data Index: 100889 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 5.0933. Min Range: -5.0933

Max Act: 3.8647. Min Act: -0.0000

Data Index: 1004255 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.0350. Min Act: -0.0000

Data Index: 1126674 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 5.0933. Min Range: -5.0933

Max Act: 4.6664. Min Act: -0.0001

Data Index: 446712 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 5.0933. Min Range: -5.0933

Max Act: 3.9885. Min Act: -0.0000

Data Index: 999829 (C4 (Web Text))

Max Activating Token Index: 526