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

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

Neuron 1597 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2953. Min Act: -0.0000

Data Index: 275303 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2649. Min Act: -0.0001

Data Index: 1139471 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2609. Min Act: -0.0000

Data Index: 315132 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2840. Min Act: -0.0001

Data Index: 1118330 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2144. Min Act: -0.0000

Data Index: 110069 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2298. Min Act: -0.0000

Data Index: 873929 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2388. Min Act: -0.0000

Data Index: 425422 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2313. Min Act: -0.0000

Data Index: 26401 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2413. Min Act: -0.0000

Data Index: 401604 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2380. Min Act: -0.0000

Data Index: 188157 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2502. Min Act: -0.0000

Data Index: 224748 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2386. Min Act: -0.0000

Data Index: 464281 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2085. Min Act: -0.0000

Data Index: 421684 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.1774. Min Act: -0.0000

Data Index: 945485 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2148. Min Act: -0.0000

Data Index: 739116 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1269084 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2269. Min Act: -0.0000

Data Index: 658903 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2254. Min Act: -0.0000

Data Index: 697093 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2254. Min Act: -0.0000

Data Index: 967965 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.2953. Min Range: -0.2953

Max Act: 0.2195. Min Act: -0.0000

Data Index: 525931 (C4 (Web Text))

Max Activating Token Index: 249