Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4118 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5443. Min Act: 0.0000

Data Index: 795639 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4868. Min Act: -0.0000

Data Index: 516887 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1286625 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4466. Min Act: -0.0000

Data Index: 25938 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4358. Min Act: 0.0000

Data Index: 718384 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1034374 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1203064 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1614799 (Python Code)

Max Activating Token Index: 469

Text #8

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3977. Min Act: -0.0000

Data Index: 92288 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3889. Min Act: -0.0000

Data Index: 257009 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3719. Min Act: -0.0000

Data Index: 573753 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1404172 (Python Code)

Max Activating Token Index: 321

Text #12

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3676. Min Act: -0.0000

Data Index: 881733 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1364781 (Python Code)

Max Activating Token Index: 973

Text #14

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3482. Min Act: -0.0000

Data Index: 613187 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1245430 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3397. Min Act: -0.0000

Data Index: 198517 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1332689 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3186. Min Act: -0.0000

Data Index: 253153 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3283. Min Act: -0.0000

Data Index: 15242 (C4 (Web Text))

Max Activating Token Index: 995