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

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

Neuron 380 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: 1.2297. Min Range: -1.2297

Max Act: 1.2297. Min Act: -0.0001

Data Index: 1212050 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0738. Min Act: -0.0001

Data Index: 473566 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.1023. Min Act: -0.0001

Data Index: 1412308 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.1027. Min Act: -0.0001

Data Index: 936356 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.1372. Min Act: -0.0001

Data Index: 51672 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.1478. Min Act: -0.0001

Data Index: 1388429 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.1150. Min Act: -0.0001

Data Index: 1564862 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0139. Min Act: -0.0001

Data Index: 1037367 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0425. Min Act: -0.0001

Data Index: 1610008 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0174. Min Act: -0.0001

Data Index: 209455 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9093. Min Act: -0.0001

Data Index: 725983 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0169. Min Act: -0.0001

Data Index: 290936 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9925. Min Act: -0.0001

Data Index: 715184 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0350. Min Act: -0.0001

Data Index: 672017 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9615. Min Act: -0.0001

Data Index: 260667 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9731. Min Act: -0.0001

Data Index: 516483 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9131. Min Act: -0.0001

Data Index: 366454 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9247. Min Act: -0.0001

Data Index: 100092 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9389. Min Act: -0.0001

Data Index: 1571652 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9336. Min Act: -0.0001

Data Index: 1286996 (C4 (Web Text))

Max Activating Token Index: 971