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

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

Neuron 4643 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.7761. Min Act: -0.0000

Data Index: 905739 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.6442. Min Act: -0.0000

Data Index: 952969 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.2176. Min Act: -0.0000

Data Index: 50783 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.1997. Min Act: -0.0000

Data Index: 371186 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1187199 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 1.7761. Min Range: -1.7761

Max Act: 1.0085. Min Act: -0.0000

Data Index: 928880 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.9351. Min Act: -0.0000

Data Index: 897850 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1041788 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.7882. Min Act: -0.0000

Data Index: 823170 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1336344 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.8322. Min Act: -0.0000

Data Index: 290611 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.8134. Min Act: -0.0000

Data Index: 30601 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.8086. Min Act: -0.0000

Data Index: 450313 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.8664. Min Act: -0.0000

Data Index: 405196 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.7600. Min Act: -0.0000

Data Index: 341015 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.6467. Min Act: -0.0000

Data Index: 678271 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.7552. Min Act: -0.0000

Data Index: 117002 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.7496. Min Act: -0.0000

Data Index: 986371 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1328720 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 1.7761. Min Range: -1.7761

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1302714 (C4 (Web Text))

Max Activating Token Index: 698