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

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

Neuron 4631 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.3053. Min Act: -0.0001

Data Index: 222581 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2819. Min Act: -0.0001

Data Index: 1018677 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2751. Min Act: -0.0001

Data Index: 1465857 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2810. Min Act: -0.0001

Data Index: 1443241 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2398. Min Act: -0.0001

Data Index: 81778 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2558. Min Act: -0.0001

Data Index: 1438819 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2395. Min Act: -0.0001

Data Index: 769377 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2532. Min Act: -0.0001

Data Index: 122122 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2538. Min Act: -0.0001

Data Index: 709864 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1616305 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2413. Min Act: -0.0001

Data Index: 639239 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2278. Min Act: -0.0001

Data Index: 1435621 (Python Code)

Max Activating Token Index: 347

Text #12

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2160. Min Act: -0.0001

Data Index: 1496270 (Python Code)

Max Activating Token Index: 838

Text #13

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1306807 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2187. Min Act: -0.0001

Data Index: 1398946 (Python Code)

Max Activating Token Index: 835

Text #15

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2248. Min Act: -0.0001

Data Index: 1461035 (Python Code)

Max Activating Token Index: 718

Text #16

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2478. Min Act: -0.0001

Data Index: 1651177 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2154. Min Act: -0.0001

Data Index: 560161 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1509792 (Python Code)

Max Activating Token Index: 878

Text #19

Max Range: 0.3053. Min Range: -0.3053

Max Act: 0.2250. Min Act: -0.0001

Data Index: 1577449 (Python Code)

Max Activating Token Index: 23