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

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

Neuron 1802 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1534748 (Python Code)

Max Activating Token Index: 431

Text #1

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1289334 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1364349 (Python Code)

Max Activating Token Index: 547

Text #3

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1594605 (Python Code)

Max Activating Token Index: 851

Text #4

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2653. Min Act: -0.0000

Data Index: 587776 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2684. Min Act: -0.0000

Data Index: 476367 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2585. Min Act: -0.0000

Data Index: 360602 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1655597 (Python Code)

Max Activating Token Index: 244

Text #8

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2268. Min Act: -0.0000

Data Index: 913029 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2260. Min Act: -0.0000

Data Index: 791266 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1583455 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2243. Min Act: -0.0000

Data Index: 314442 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2186. Min Act: -0.0000

Data Index: 513095 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2279. Min Act: -0.0000

Data Index: 897922 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2112. Min Act: -0.0000

Data Index: 417518 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1474886 (Python Code)

Max Activating Token Index: 720

Text #16

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1646030 (Python Code)

Max Activating Token Index: 856

Text #17

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1353732 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1978. Min Act: -0.0000

Data Index: 713839 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.2948. Min Range: -0.2948

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1069221 (C4 (Web Text))

Max Activating Token Index: 646