Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1746 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.3346. Min Act: -0.0001

Data Index: 1358624 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2596. Min Act: -0.0001

Data Index: 708858 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2526. Min Act: -0.0001

Data Index: 854248 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2565. Min Act: -0.0001

Data Index: 446661 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2536. Min Act: -0.0001

Data Index: 403502 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2432. Min Act: -0.0001

Data Index: 264649 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2391. Min Act: -0.0001

Data Index: 826210 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2469. Min Act: -0.0001

Data Index: 640200 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2296. Min Act: -0.0001

Data Index: 792655 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2344. Min Act: -0.0001

Data Index: 1133971 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2414. Min Act: -0.0001

Data Index: 652584 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2338. Min Act: -0.0001

Data Index: 1015418 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2266. Min Act: -0.0001

Data Index: 693304 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2182. Min Act: -0.0001

Data Index: 896539 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2248. Min Act: -0.0001

Data Index: 793118 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2294. Min Act: -0.0001

Data Index: 669322 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2230. Min Act: -0.0001

Data Index: 484713 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2135. Min Act: -0.0001

Data Index: 227085 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2120. Min Act: -0.0001

Data Index: 998393 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.3346. Min Range: -0.3346

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1153296 (C4 (Web Text))

Max Activating Token Index: 844