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

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

Neuron 4536 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: 0.6576. Min Range: -0.6576

Max Act: 0.6576. Min Act: -0.0000

Data Index: 787502 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.5022. Min Act: -0.0000

Data Index: 765951 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4389. Min Act: -0.0000

Data Index: 360788 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4339. Min Act: -0.0000

Data Index: 762472 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1278634 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3968. Min Act: -0.0000

Data Index: 1172619 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1337729 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3845. Min Act: -0.0000

Data Index: 429465 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4270. Min Act: -0.0000

Data Index: 754989 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1311602 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4338. Min Act: -0.0000

Data Index: 407820 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3878. Min Act: -0.0000

Data Index: 793634 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4274. Min Act: -0.0000

Data Index: 112863 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4108. Min Act: -0.0000

Data Index: 407620 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1230293 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4077. Min Act: -0.0000

Data Index: 620607 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4041. Min Act: -0.0000

Data Index: 995844 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4091. Min Act: -0.0000

Data Index: 169381 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.4209. Min Act: -0.0000

Data Index: 931626 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.6576. Min Range: -0.6576

Max Act: 0.3592. Min Act: -0.0000

Data Index: 70374 (C4 (Web Text))

Max Activating Token Index: 191