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

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

Neuron 2475 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.3055. Min Act: -0.0000

Data Index: 137708 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.3149. Min Act: -0.0000

Data Index: 274398 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2893. Min Act: -0.0000

Data Index: 275030 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2944. Min Act: -0.0000

Data Index: 340712 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2746. Min Act: -0.0000

Data Index: 486214 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2549. Min Act: -0.0000

Data Index: 108705 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2629. Min Act: -0.0000

Data Index: 859341 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2540. Min Act: -0.0000

Data Index: 530385 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2366. Min Act: -0.0000

Data Index: 271069 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2254. Min Act: -0.0000

Data Index: 330956 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1006334 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2303. Min Act: -0.0000

Data Index: 509275 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2351. Min Act: -0.0000

Data Index: 613368 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1188969 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1245 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2265. Min Act: -0.0000

Data Index: 242449 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2391. Min Act: -0.0000

Data Index: 772250 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2118. Min Act: -0.0000

Data Index: 269224 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2162. Min Act: -0.0000

Data Index: 290999 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.3149. Min Range: -0.3149

Max Act: 0.2290. Min Act: 0.0000

Data Index: 235368 (C4 (Web Text))

Max Activating Token Index: 63