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

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

Neuron 5200 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.7602. Min Act: -0.0000

Data Index: 8812 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.8316. Min Act: -0.0000

Data Index: 935721 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.3700. Min Act: -0.0000

Data Index: 279510 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.2825. Min Act: -0.0000

Data Index: 598532 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.2770. Min Act: -0.0000

Data Index: 1283482 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.4509. Min Act: -0.0000

Data Index: 874887 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.5718. Min Act: -0.0000

Data Index: 1052786 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.5369. Min Act: -0.0000

Data Index: 675824 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.1364. Min Act: -0.0000

Data Index: 211519 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.3977. Min Act: -0.0000

Data Index: 742316 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.1093. Min Act: -0.0000

Data Index: 1002177 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.5306. Min Act: -0.0000

Data Index: 9685 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.0067. Min Act: -0.0000

Data Index: 316269 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 5.8316. Min Range: -5.8316

Max Act: 4.9629. Min Act: -0.0000

Data Index: 127379 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.2190. Min Act: -0.0000

Data Index: 917190 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 5.8316. Min Range: -5.8316

Max Act: 4.7803. Min Act: -0.0000

Data Index: 879089 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 5.8316. Min Range: -5.8316

Max Act: 5.0844. Min Act: -0.0000

Data Index: 80712 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 5.8316. Min Range: -5.8316

Max Act: 4.5665. Min Act: -0.0000

Data Index: 495437 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 5.8316. Min Range: -5.8316

Max Act: 4.4302. Min Act: -0.0000

Data Index: 1131417 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 5.8316. Min Range: -5.8316

Max Act: 4.2061. Min Act: -0.0000

Data Index: 362559 (C4 (Web Text))

Max Activating Token Index: 966