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

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

Neuron 1621 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0818. Min Range: -2.0818

Max Act: 2.0818. Min Act: -0.0000

Data Index: 1017592 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.7585. Min Act: -0.0000

Data Index: 377849 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.6979. Min Act: -0.0000

Data Index: 1292679 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.5942. Min Act: -0.0000

Data Index: 876915 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.6191. Min Act: -0.0000

Data Index: 677743 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.5262. Min Act: -0.0000

Data Index: 270565 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.4571. Min Act: -0.0000

Data Index: 266290 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.5243. Min Act: -0.0000

Data Index: 678904 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.3968. Min Act: -0.0000

Data Index: 671996 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.3333. Min Act: -0.0000

Data Index: 380328 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.4727. Min Act: -0.0000

Data Index: 804048 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.4659. Min Act: 0.0000

Data Index: 394180 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1200603 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.2907. Min Act: -0.0000

Data Index: 1284798 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.3453. Min Act: -0.0000

Data Index: 1084423 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.4338. Min Act: -0.0000

Data Index: 110187 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.3682. Min Act: -0.0000

Data Index: 192132 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.3428. Min Act: -0.0000

Data Index: 187160 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.2699. Min Act: -0.0000

Data Index: 330505 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 2.0818. Min Range: -2.0818

Max Act: 1.3859. Min Act: -0.0000

Data Index: 691152 (C4 (Web Text))

Max Activating Token Index: 852