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

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

Neuron 2866 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.6356. Min Act: -0.0001

Data Index: 700510 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5749. Min Act: -0.0001

Data Index: 321960 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5420. Min Act: -0.0001

Data Index: 367586 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5584. Min Act: -0.0001

Data Index: 1176390 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5688. Min Act: -0.0001

Data Index: 225506 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5556. Min Act: -0.0001

Data Index: 814385 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5506. Min Act: -0.0001

Data Index: 1151582 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5453. Min Act: -0.0001

Data Index: 530643 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5673. Min Act: -0.0001

Data Index: 1067689 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5445. Min Act: -0.0001

Data Index: 910909 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5412. Min Act: -0.0001

Data Index: 696708 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5413. Min Act: -0.0001

Data Index: 1149761 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5333. Min Act: -0.0001

Data Index: 1048596 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5177. Min Act: -0.0001

Data Index: 1149062 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5397. Min Act: -0.0001

Data Index: 624418 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5192. Min Act: -0.0001

Data Index: 330682 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5373. Min Act: -0.0001

Data Index: 258949 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5356. Min Act: -0.0001

Data Index: 550511 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5290. Min Act: -0.0001

Data Index: 1299689 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5303. Min Act: -0.0001

Data Index: 858451 (C4 (Web Text))

Max Activating Token Index: 794