Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 345 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.8145. Min Act: -0.0001

Data Index: 1230928 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.5281. Min Act: -0.0001

Data Index: 511644 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.5802. Min Act: -0.0001

Data Index: 58911 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.4975. Min Act: -0.0001

Data Index: 779932 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.4062. Min Act: -0.0001

Data Index: 902022 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.4160. Min Act: -0.0001

Data Index: 478226 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.4472. Min Act: -0.0001

Data Index: 13858 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2344. Min Act: -0.0001

Data Index: 325490 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2906. Min Act: -0.0001

Data Index: 439275 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.3567. Min Act: -0.0001

Data Index: 895390 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2384. Min Act: -0.0001

Data Index: 348206 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2713. Min Act: -0.0001

Data Index: 891767 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.1228. Min Act: -0.0001

Data Index: 1107599 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2423. Min Act: -0.0001

Data Index: 703570 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.0173. Min Act: -0.0001

Data Index: 986559 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.1526. Min Act: -0.0001

Data Index: 982594 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.0731. Min Act: -0.0001

Data Index: 516016 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2762. Min Act: -0.0001

Data Index: 384778 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.1929. Min Act: -0.0001

Data Index: 778156 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.1225. Min Act: -0.0001

Data Index: 1272728 (C4 (Web Text))

Max Activating Token Index: 1008