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

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

Neuron 2717 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3627. Min Act: -0.0000

Data Index: 994856 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1112673 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3082. Min Act: -0.0000

Data Index: 453101 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2924. Min Act: -0.0000

Data Index: 23607 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1162177 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2606. Min Act: -0.0000

Data Index: 637138 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1190252 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1337268 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2445. Min Act: -0.0000

Data Index: 115648 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2419. Min Act: -0.0000

Data Index: 741184 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2503. Min Act: -0.0000

Data Index: 917367 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2356. Min Act: -0.0000

Data Index: 499371 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2455. Min Act: -0.0000

Data Index: 38782 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1335091 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2335. Min Act: -0.0000

Data Index: 419252 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1238905 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2353. Min Act: -0.0000

Data Index: 280501 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2192. Min Act: -0.0000

Data Index: 972274 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2201. Min Act: -0.0000

Data Index: 563618 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1350597 (C4 (Web Text))

Max Activating Token Index: 242