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

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

Neuron 122 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: 0.7336. Min Range: -0.7336

Max Act: 0.7336. Min Act: -0.0000

Data Index: 71364 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.6532. Min Act: -0.0000

Data Index: 204934 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5227. Min Act: -0.0000

Data Index: 889816 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5402. Min Act: -0.0000

Data Index: 245676 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5737. Min Act: -0.0000

Data Index: 16426 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1349751 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5581. Min Act: -0.0000

Data Index: 684301 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5668. Min Act: 0.0000

Data Index: 673136 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.5689. Min Act: -0.0000

Data Index: 662077 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4815. Min Act: -0.0000

Data Index: 782281 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4625. Min Act: -0.0000

Data Index: 419792 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4617. Min Act: -0.0000

Data Index: 387373 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4259. Min Act: -0.0000

Data Index: 339079 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4293. Min Act: -0.0000

Data Index: 126148 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1084213 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4581. Min Act: -0.0000

Data Index: 357699 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4247. Min Act: -0.0000

Data Index: 45453 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4374. Min Act: 0.0000

Data Index: 149545 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4228. Min Act: 0.0000

Data Index: 334492 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.7336. Min Range: -0.7336

Max Act: 0.4083. Min Act: -0.0000

Data Index: 729535 (C4 (Web Text))

Max Activating Token Index: 530