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

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

Neuron 4623 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: 1.9610. Min Range: -1.9610

Max Act: 1.9610. Min Act: -0.0000

Data Index: 892274 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.9335. Min Act: -0.0000

Data Index: 511211 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.8823. Min Act: -0.0000

Data Index: 797430 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.8038. Min Act: -0.0000

Data Index: 694167 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.6665. Min Act: -0.0000

Data Index: 29541 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.7418. Min Act: -0.0000

Data Index: 386408 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.6169. Min Act: -0.0000

Data Index: 1214674 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.4902. Min Act: -0.0000

Data Index: 560626 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.5575. Min Act: -0.0000

Data Index: 426137 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.4317. Min Act: -0.0000

Data Index: 711429 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.6038. Min Act: -0.0000

Data Index: 20198 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.4614. Min Act: -0.0000

Data Index: 695342 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.4382. Min Act: -0.0000

Data Index: 83705 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.4415. Min Act: -0.0000

Data Index: 1239957 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.4290. Min Act: -0.0000

Data Index: 884160 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.3844. Min Act: -0.0000

Data Index: 794035 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.3907. Min Act: -0.0000

Data Index: 741097 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.3007. Min Act: -0.0000

Data Index: 286050 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.4644. Min Act: -0.0000

Data Index: 1323604 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.9610. Min Range: -1.9610

Max Act: 1.3712. Min Act: -0.0000

Data Index: 1197741 (C4 (Web Text))

Max Activating Token Index: 684