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

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

Neuron 1873 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: 3.1667. Min Range: -3.1667

Max Act: 3.1667. Min Act: -0.0000

Data Index: 227283 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.6766. Min Act: -0.0000

Data Index: 984758 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.3569. Min Act: -0.0000

Data Index: 1272277 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.5042. Min Act: -0.0000

Data Index: 1257071 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.2023. Min Act: -0.0000

Data Index: 349538 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.2567. Min Act: -0.0000

Data Index: 538265 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.2506. Min Act: -0.0000

Data Index: 834193 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.2126. Min Act: -0.0000

Data Index: 1347248 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.1969. Min Act: -0.0000

Data Index: 952536 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.1977. Min Act: -0.0000

Data Index: 1270489 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.1680. Min Act: -0.0000

Data Index: 960081 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.0441. Min Act: -0.0000

Data Index: 501376 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.0936. Min Act: -0.0000

Data Index: 1052069 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 3.1667. Min Range: -3.1667

Max Act: 1.9578. Min Act: -0.0000

Data Index: 400238 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.0391. Min Act: -0.0000

Data Index: 70359 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.0215. Min Act: -0.0000

Data Index: 1493261 (Python Code)

Max Activating Token Index: 572

Text #16

Max Range: 3.1667. Min Range: -3.1667

Max Act: 1.9064. Min Act: -0.0000

Data Index: 491810 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 3.1667. Min Range: -3.1667

Max Act: 2.2443. Min Act: -0.0000

Data Index: 66893 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 3.1667. Min Range: -3.1667

Max Act: 1.7926. Min Act: -0.0000

Data Index: 531257 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 3.1667. Min Range: -3.1667

Max Act: 1.9847. Min Act: -0.0000

Data Index: 1179308 (C4 (Web Text))

Max Activating Token Index: 17