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

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

Neuron 2410 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.5210. Min Act: -0.0000

Data Index: 989170 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4492. Min Act: -0.0000

Data Index: 918216 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3942. Min Act: -0.0000

Data Index: 603484 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3706. Min Act: -0.0000

Data Index: 735978 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3168. Min Act: -0.0000

Data Index: 202512 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3135. Min Act: -0.0001

Data Index: 375382 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3192. Min Act: -0.0001

Data Index: 414314 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3119. Min Act: -0.0000

Data Index: 866601 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2868. Min Act: -0.0000

Data Index: 236795 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1281949 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3016. Min Act: -0.0001

Data Index: 1223178 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2936. Min Act: -0.0000

Data Index: 739509 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3141. Min Act: -0.0000

Data Index: 894585 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2906. Min Act: -0.0000

Data Index: 718951 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2686. Min Act: -0.0000

Data Index: 32689 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2577. Min Act: -0.0000

Data Index: 989034 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2530. Min Act: -0.0000

Data Index: 377525 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2608. Min Act: -0.0000

Data Index: 214952 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2478. Min Act: -0.0001

Data Index: 449240 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2356. Min Act: -0.0000

Data Index: 305338 (C4 (Web Text))

Max Activating Token Index: 672