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

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

Neuron 5911 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: 2.2418. Min Range: -2.2418

Max Act: 2.2418. Min Act: -0.0000

Data Index: 939204 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.8287. Min Act: -0.0000

Data Index: 612730 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1286630 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.6270. Min Act: -0.0000

Data Index: 1178660 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.6585. Min Act: -0.0000

Data Index: 1190773 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.6474. Min Act: -0.0000

Data Index: 1052329 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.6240. Min Act: -0.0000

Data Index: 1168381 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.5320. Min Act: -0.0000

Data Index: 387197 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1257121 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.4839. Min Act: -0.0000

Data Index: 972644 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.4572. Min Act: -0.0000

Data Index: 107077 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.4490. Min Act: -0.0000

Data Index: 1321358 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.4355. Min Act: -0.0000

Data Index: 729912 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.4179. Min Act: -0.0000

Data Index: 1006318 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.2949. Min Act: -0.0000

Data Index: 217093 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.4267. Min Act: -0.0000

Data Index: 50937 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1043727 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.2366. Min Act: -0.0000

Data Index: 798602 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.2858. Min Act: -0.0000

Data Index: 826991 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 2.2418. Min Range: -2.2418

Max Act: 1.2086. Min Act: -0.0000

Data Index: 728261 (C4 (Web Text))

Max Activating Token Index: 872