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

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

Neuron 5646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.2749. Min Act: -0.0000

Data Index: 611865 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0227. Min Act: -0.0000

Data Index: 509204 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.2749. Min Range: -1.2749

Max Act: 1.0759. Min Act: -0.0000

Data Index: 974908 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1032314 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.8902. Min Act: -0.0000

Data Index: 761852 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.8870. Min Act: -0.0000

Data Index: 152742 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.8356. Min Act: -0.0000

Data Index: 892224 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.8250. Min Act: -0.0000

Data Index: 634161 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.8486. Min Act: -0.0000

Data Index: 577040 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.8182. Min Act: -0.0000

Data Index: 18943 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.8378. Min Act: -0.0000

Data Index: 376912 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1028104 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.7911. Min Act: -0.0000

Data Index: 959061 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.7672. Min Act: -0.0000

Data Index: 10852 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1232354 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1002680 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1329404 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.8129. Min Act: -0.0000

Data Index: 403355 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.7841. Min Act: -0.0000

Data Index: 225966 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 1.2749. Min Range: -1.2749

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1351981 (C4 (Web Text))

Max Activating Token Index: 52