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

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

Neuron 2764 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.6486. Min Act: -0.0000

Data Index: 838170 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1212186 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1235850 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.5249. Min Act: -0.0000

Data Index: 420779 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.5035. Min Act: -0.0000

Data Index: 17296 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4873. Min Act: -0.0000

Data Index: 280419 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4984. Min Act: -0.0000

Data Index: 816588 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1129104 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1183309 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4421. Min Act: -0.0000

Data Index: 73878 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4834. Min Act: -0.0000

Data Index: 923592 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1247242 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4441. Min Act: -0.0000

Data Index: 169666 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4410. Min Act: -0.0000

Data Index: 704464 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4428. Min Act: -0.0000

Data Index: 60951 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1227965 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4357. Min Act: -0.0000

Data Index: 425544 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4485. Min Act: -0.0000

Data Index: 496154 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1205875 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.6486. Min Range: -0.6486

Max Act: 0.4044. Min Act: 0.0000

Data Index: 268561 (C4 (Web Text))

Max Activating Token Index: 847