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

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

Neuron 3649 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7391. Min Act: -0.0000

Data Index: 301046 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6052. Min Act: -0.0000

Data Index: 348985 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1173818 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1092741 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4918. Min Act: -0.0000

Data Index: 602456 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5036. Min Act: -0.0000

Data Index: 220609 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4390. Min Act: -0.0000

Data Index: 100590 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4648. Min Act: -0.0000

Data Index: 147985 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4640. Min Act: -0.0000

Data Index: 514491 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4586. Min Act: -0.0000

Data Index: 904835 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4542. Min Act: -0.0000

Data Index: 262213 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1210600 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1555607 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1255535 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4241. Min Act: -0.0000

Data Index: 299020 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4458. Min Act: -0.0000

Data Index: 592304 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.3958. Min Act: -0.0000

Data Index: 914172 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4074. Min Act: -0.0000

Data Index: 68649 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1346006 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.4137. Min Act: -0.0000

Data Index: 1043719 (C4 (Web Text))

Max Activating Token Index: 567