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

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

Neuron 2185 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0554. Min Range: -1.0554

Max Act: 1.0203. Min Act: -0.0000

Data Index: 856122 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 1.0554. Min Range: -1.0554

Max Act: 1.0554. Min Act: -0.0000

Data Index: 553541 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.9540. Min Act: -0.0000

Data Index: 295892 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.9847. Min Act: -0.0001

Data Index: 971357 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.9361. Min Act: -0.0000

Data Index: 629743 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8674. Min Act: -0.0000

Data Index: 1345255 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8645. Min Act: -0.0000

Data Index: 366886 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8433. Min Act: -0.0001

Data Index: 1474460 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8262. Min Act: -0.0000

Data Index: 824431 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1127359 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8462. Min Act: -0.0000

Data Index: 914210 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1090954 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8355. Min Act: -0.0000

Data Index: 604887 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8552. Min Act: -0.0000

Data Index: 836704 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1223218 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8496. Min Act: -0.0000

Data Index: 853209 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8275. Min Act: -0.0001

Data Index: 1386370 (Python Code)

Max Activating Token Index: 598

Text #17

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1033121 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8138. Min Act: -0.0000

Data Index: 588928 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 1.0554. Min Range: -1.0554

Max Act: 0.8110. Min Act: -0.0001

Data Index: 797813 (C4 (Web Text))

Max Activating Token Index: 1000