Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4089 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.3666. Min Act: -0.0000

Data Index: 277470 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9272. Min Act: -0.0000

Data Index: 944107 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9345. Min Act: -0.0000

Data Index: 865894 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9345. Min Act: -0.0000

Data Index: 143914 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9569. Min Act: -0.0000

Data Index: 945464 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8270. Min Act: -0.0000

Data Index: 798898 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8298. Min Act: -0.0001

Data Index: 156065 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8298. Min Act: -0.0000

Data Index: 950940 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8189. Min Act: -0.0001

Data Index: 1068337 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7330. Min Act: -0.0000

Data Index: 662315 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7427. Min Act: -0.0000

Data Index: 683447 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1326715 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1056503 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7241. Min Act: -0.0000

Data Index: 473438 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7145. Min Act: -0.0000

Data Index: 591375 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7359. Min Act: -0.0000

Data Index: 448005 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7173. Min Act: -0.0001

Data Index: 317558 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7560. Min Act: -0.0000

Data Index: 741899 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7078. Min Act: -0.0000

Data Index: 336560 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1057232 (C4 (Web Text))

Max Activating Token Index: 731