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

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

Neuron 6004 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1786. Min Range: -2.1786

Max Act: 2.1786. Min Act: -0.0002

Data Index: 1320101 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.8087. Min Act: -0.0002

Data Index: 776789 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.7065. Min Act: -0.0002

Data Index: 1326776 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.7138. Min Act: -0.0002

Data Index: 953038 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.6588. Min Act: -0.0002

Data Index: 973293 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.4260. Min Act: -0.0002

Data Index: 1289134 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.3544. Min Act: -0.0002

Data Index: 1218322 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.3689. Min Act: -0.0002

Data Index: 578360 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.3016. Min Act: -0.0002

Data Index: 762304 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.2645. Min Act: -0.0002

Data Index: 46024 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.2658. Min Act: -0.0002

Data Index: 451285 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.2555. Min Act: -0.0002

Data Index: 713220 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.2378. Min Act: -0.0002

Data Index: 904530 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.2406. Min Act: -0.0002

Data Index: 49968 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.2310. Min Act: -0.0002

Data Index: 63883 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.1942. Min Act: -0.0002

Data Index: 185714 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.2179. Min Act: -0.0002

Data Index: 1005958 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.1861. Min Act: -0.0002

Data Index: 251440 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.2386. Min Act: -0.0002

Data Index: 559840 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 2.1786. Min Range: -2.1786

Max Act: 1.2166. Min Act: -0.0002

Data Index: 386338 (C4 (Web Text))

Max Activating Token Index: 40