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

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

Neuron 646 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: 0.5995. Min Range: -0.5995

Max Act: 0.5995. Min Act: -0.0000

Data Index: 971383 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.5882. Min Act: -0.0000

Data Index: 641398 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1086481 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4970. Min Act: -0.0000

Data Index: 477530 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.5193. Min Act: -0.0000

Data Index: 1059684 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.5087. Min Act: -0.0000

Data Index: 477513 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.5002. Min Act: -0.0000

Data Index: 198416 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4765. Min Act: 0.0000

Data Index: 278828 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4814. Min Act: -0.0000

Data Index: 85683 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1084147 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1286548 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4418. Min Act: -0.0000

Data Index: 396739 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1127821 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4306. Min Act: -0.0000

Data Index: 533243 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4294. Min Act: -0.0000

Data Index: 833026 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4494. Min Act: -0.0000

Data Index: 307246 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4411. Min Act: -0.0000

Data Index: 546958 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4035. Min Act: 0.0000

Data Index: 1179198 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4405. Min Act: -0.0000

Data Index: 935284 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 0.5995. Min Range: -0.5995

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1145527 (C4 (Web Text))

Max Activating Token Index: 92