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

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

Neuron 3860 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.4527. Min Act: 0.0001

Data Index: 298149 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3533. Min Act: -0.0000

Data Index: 361282 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3429. Min Act: -0.0000

Data Index: 383655 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3459. Min Act: 0.0001

Data Index: 1349604 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3439. Min Act: 0.0001

Data Index: 807677 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3321. Min Act: -0.0000

Data Index: 626253 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3305. Min Act: -0.0000

Data Index: 602473 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3300. Min Act: 0.0001

Data Index: 364329 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3395. Min Act: 0.0001

Data Index: 397771 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3155. Min Act: -0.0000

Data Index: 842451 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3242. Min Act: 0.0001

Data Index: 616086 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3132. Min Act: 0.0001

Data Index: 614805 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3133. Min Act: -0.0000

Data Index: 995081 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3099. Min Act: 0.0000

Data Index: 1194922 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3001. Min Act: -0.0000

Data Index: 1274043 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1212223 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3069. Min Act: -0.0001

Data Index: 647461 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.2966. Min Act: 0.0001

Data Index: 1336545 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3041. Min Act: 0.0001

Data Index: 115200 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.4527. Min Range: -0.4527

Max Act: 0.3167. Min Act: -0.0000

Data Index: 41337 (C4 (Web Text))

Max Activating Token Index: 470