Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2879 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.9428. Min Act: -0.0001

Data Index: 910125 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.7640. Min Act: -0.0001

Data Index: 743637 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.9412. Min Act: -0.0001

Data Index: 154635 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.8845. Min Act: -0.0001

Data Index: 727316 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.7753. Min Act: -0.0001

Data Index: 413493 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.6088. Min Act: -0.0001

Data Index: 427917 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.5133. Min Act: -0.0001

Data Index: 890980 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.4965. Min Act: -0.0001

Data Index: 876993 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.4578. Min Act: -0.0001

Data Index: 710802 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.5323. Min Act: -0.0001

Data Index: 568486 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.3700. Min Act: -0.0001

Data Index: 597249 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.4086. Min Act: -0.0001

Data Index: 1032428 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.3223. Min Act: -0.0001

Data Index: 129988 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.3763. Min Act: -0.0001

Data Index: 21097 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.2955. Min Act: -0.0001

Data Index: 357010 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.3609. Min Act: -0.0001

Data Index: 537378 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.3166. Min Act: -0.0001

Data Index: 893475 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.4309. Min Act: -0.0001

Data Index: 1028661 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.4186. Min Act: -0.0001

Data Index: 1291038 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.9428. Min Range: -1.9428

Max Act: 1.3399. Min Act: -0.0001

Data Index: 119736 (C4 (Web Text))

Max Activating Token Index: 990