Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4589 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.3104. Min Act: 0.0000

Data Index: 875912 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1299602 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2645. Min Act: -0.0000

Data Index: 107785 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2783. Min Act: 0.0000

Data Index: 1539670 (Python Code)

Max Activating Token Index: 534

Text #4

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2509. Min Act: 0.0000

Data Index: 382306 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2338. Min Act: 0.0000

Data Index: 916009 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2224. Min Act: 0.0001

Data Index: 1043544 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2206. Min Act: -0.0000

Data Index: 78879 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1460757 (Python Code)

Max Activating Token Index: 740

Text #9

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1634901 (Python Code)

Max Activating Token Index: 965

Text #10

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2228. Min Act: -0.0000

Data Index: 684304 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1050906 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1120924 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.1961. Min Act: -0.0000

Data Index: 4745 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1407478 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1531604 (Python Code)

Max Activating Token Index: 402

Text #16

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2083. Min Act: -0.0000

Data Index: 884155 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2167. Min Act: -0.0000

Data Index: 878251 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2023. Min Act: -0.0000

Data Index: 406492 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1240679 (C4 (Web Text))

Max Activating Token Index: 677