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

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

Neuron 4203 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: 0.5319. Min Range: -0.5319

Max Act: 0.5154. Min Act: -0.0000

Data Index: 166932 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.5319. Min Act: -0.0000

Data Index: 301215 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4942. Min Act: -0.0000

Data Index: 908450 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4538. Min Act: -0.0000

Data Index: 109946 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4674. Min Act: -0.0000

Data Index: 677282 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4671. Min Act: -0.0000

Data Index: 614332 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4000. Min Act: -0.0000

Data Index: 609006 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4379. Min Act: -0.0000

Data Index: 9277 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4090. Min Act: -0.0000

Data Index: 472280 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1308943 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1353902 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.4053. Min Act: 0.0000

Data Index: 8277 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1345707 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3581. Min Act: -0.0000

Data Index: 27817 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1271529 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3556. Min Act: -0.0000

Data Index: 952486 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1289994 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3588. Min Act: -0.0000

Data Index: 638755 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3301. Min Act: 0.0000

Data Index: 58042 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3543. Min Act: 0.0000

Data Index: 397077 (C4 (Web Text))

Max Activating Token Index: 410