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

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

Neuron 3845 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.8504. Min Act: -0.0000

Data Index: 964820 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.6822. Min Act: -0.0000

Data Index: 1271962 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.7223. Min Act: -0.0000

Data Index: 92516 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.5392. Min Act: -0.0000

Data Index: 127442 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.3740. Min Act: -0.0000

Data Index: 151712 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2850. Min Act: -0.0000

Data Index: 97951 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.3484. Min Act: -0.0000

Data Index: 1347713 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1036407 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2910. Min Act: -0.0000

Data Index: 49835 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1557019 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2641. Min Act: -0.0000

Data Index: 462734 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.3316. Min Act: -0.0000

Data Index: 946241 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2398. Min Act: -0.0000

Data Index: 1191423 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.1822. Min Act: -0.0000

Data Index: 576760 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2491. Min Act: -0.0000

Data Index: 451521 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2450. Min Act: -0.0000

Data Index: 994257 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2414. Min Act: -0.0000

Data Index: 225303 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2089. Min Act: -0.0000

Data Index: 539783 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.2149. Min Act: -0.0000

Data Index: 1032853 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 1.8504. Min Range: -1.8504

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1144310 (C4 (Web Text))

Max Activating Token Index: 378