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

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

Neuron 4680 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9411. Min Act: -0.0001

Data Index: 1127677 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9306. Min Act: -0.0001

Data Index: 900157 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9640. Min Act: -0.0001

Data Index: 1302113 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9360. Min Act: -0.0001

Data Index: 154404 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9607. Min Act: -0.0001

Data Index: 1154579 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8922. Min Act: -0.0001

Data Index: 469986 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8856. Min Act: -0.0001

Data Index: 779926 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9509. Min Act: -0.0001

Data Index: 526159 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8404. Min Act: -0.0001

Data Index: 716334 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8681. Min Act: -0.0001

Data Index: 808387 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8542. Min Act: -0.0001

Data Index: 181261 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8961. Min Act: -0.0001

Data Index: 537857 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9227. Min Act: -0.0001

Data Index: 678295 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9183. Min Act: -0.0001

Data Index: 761952 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8253. Min Act: -0.0001

Data Index: 441562 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7126. Min Act: -0.0001

Data Index: 277321 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9245. Min Act: -0.0001

Data Index: 1218057 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8465. Min Act: -0.0001

Data Index: 444091 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8545. Min Act: -0.0001

Data Index: 529310 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8563. Min Act: -0.0001

Data Index: 838556 (C4 (Web Text))

Max Activating Token Index: 68