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

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

Neuron 156 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1333674 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2866. Min Act: -0.0000

Data Index: 611256 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2859. Min Act: -0.0000

Data Index: 65318 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1396827 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2563. Min Act: -0.0000

Data Index: 1197325 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2392. Min Act: -0.0001

Data Index: 1566188 (Python Code)

Max Activating Token Index: 633

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1168356 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1201397 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2267. Min Act: -0.0000

Data Index: 93876 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1434996 (Python Code)

Max Activating Token Index: 662

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2183. Min Act: -0.0001

Data Index: 1095535 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1456731 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1093389 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1058046 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2171. Min Act: -0.0000

Data Index: 466869 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1175763 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1480738 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2168. Min Act: -0.0000

Data Index: 91980 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2173. Min Act: -0.0001

Data Index: 1508787 (Python Code)

Max Activating Token Index: 72

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2019. Min Act: -0.0000

Data Index: 355698 (C4 (Web Text))

Max Activating Token Index: 699