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

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

Neuron 1937 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.6026. Min Act: -0.0001

Data Index: 1400400 (Python Code)

Max Activating Token Index: 302

Text #1

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.5221. Min Act: -0.0001

Data Index: 1556858 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4787. Min Act: -0.0001

Data Index: 1451837 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4723. Min Act: -0.0001

Data Index: 1384896 (Python Code)

Max Activating Token Index: 55

Text #4

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4246. Min Act: -0.0001

Data Index: 1570974 (Python Code)

Max Activating Token Index: 359

Text #5

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4465. Min Act: -0.0001

Data Index: 1573498 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4355. Min Act: -0.0001

Data Index: 1479413 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4184. Min Act: -0.0001

Data Index: 1532867 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4458. Min Act: -0.0001

Data Index: 1361072 (Python Code)

Max Activating Token Index: 396

Text #9

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4326. Min Act: -0.0001

Data Index: 951970 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4254. Min Act: -0.0001

Data Index: 714846 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4052. Min Act: -0.0001

Data Index: 1651044 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4033. Min Act: -0.0001

Data Index: 1578063 (Python Code)

Max Activating Token Index: 951

Text #13

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4130. Min Act: -0.0001

Data Index: 1452546 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4078. Min Act: -0.0001

Data Index: 1405748 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4065. Min Act: -0.0001

Data Index: 1553512 (Python Code)

Max Activating Token Index: 209

Text #16

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1280534 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3946. Min Act: -0.0001

Data Index: 1579023 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3677. Min Act: -0.0001

Data Index: 1511217 (Python Code)

Max Activating Token Index: 361

Text #19

Max Range: 0.6026. Min Range: -0.6026

Max Act: 0.3780. Min Act: -0.0001

Data Index: 878056 (C4 (Web Text))

Max Activating Token Index: 398