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

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

Neuron 4176 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3541. Min Range: -2.3541

Max Act: 2.3439. Min Act: -0.0000

Data Index: 587116 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 2.3541. Min Range: -2.3541

Max Act: 2.2467. Min Act: -0.0000

Data Index: 698354 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 2.3541. Min Range: -2.3541

Max Act: 2.1363. Min Act: -0.0000

Data Index: 223652 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.3541. Min Range: -2.3541

Max Act: 2.3541. Min Act: -0.0000

Data Index: 494176 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 2.3541. Min Range: -2.3541

Max Act: 2.2271. Min Act: -0.0000

Data Index: 607205 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 2.3541. Min Range: -2.3541

Max Act: 2.1544. Min Act: -0.0000

Data Index: 1183398 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 2.3541. Min Range: -2.3541

Max Act: 2.1248. Min Act: -0.0000

Data Index: 521692 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.9439. Min Act: -0.0000

Data Index: 220082 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 2.3541. Min Range: -2.3541

Max Act: 2.0393. Min Act: -0.0000

Data Index: 667228 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.9066. Min Act: -0.0000

Data Index: 1246149 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.8814. Min Act: -0.0000

Data Index: 271755 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.8561. Min Act: -0.0000

Data Index: 193290 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.8009. Min Act: -0.0000

Data Index: 113979 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.7423. Min Act: -0.0000

Data Index: 1233483 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.8540. Min Act: -0.0000

Data Index: 1011918 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.7420. Min Act: -0.0000

Data Index: 860356 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.6242. Min Act: -0.0000

Data Index: 1330313 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.5850. Min Act: -0.0000

Data Index: 494183 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.5509. Min Act: -0.0000

Data Index: 1050417 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 2.3541. Min Range: -2.3541

Max Act: 1.5191. Min Act: -0.0000

Data Index: 129426 (C4 (Web Text))

Max Activating Token Index: 641