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

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

Neuron 50 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0309. Min Act: -0.0001

Data Index: 833267 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1120932 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1117387 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0307. Min Act: -0.0001

Data Index: 928245 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0298. Min Act: -0.0001

Data Index: 617115 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0300. Min Act: -0.0001

Data Index: 435353 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0296. Min Act: -0.0001

Data Index: 253043 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0296. Min Act: -0.0001

Data Index: 764157 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0296. Min Act: -0.0001

Data Index: 909303 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0301. Min Act: -0.0001

Data Index: 478024 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0294. Min Act: -0.0001

Data Index: 139555 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0294. Min Act: -0.0001

Data Index: 890916 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0295. Min Act: -0.0001

Data Index: 898230 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1133405 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0298. Min Act: -0.0001

Data Index: 929193 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0300. Min Act: -0.0001

Data Index: 907243 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1112466 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1223040 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0287. Min Act: -0.0001

Data Index: 852001 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.0310. Min Range: -0.0310

Max Act: 0.0293. Min Act: -0.0001

Data Index: 806741 (C4 (Web Text))

Max Activating Token Index: 141