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

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

Neuron 1831 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.5186. Min Act: -0.0001

Data Index: 195932 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.4253. Min Act: -0.0001

Data Index: 544774 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.2385. Min Act: -0.0001

Data Index: 1224319 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.3657. Min Act: -0.0000

Data Index: 757290 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.4272. Min Act: -0.0001

Data Index: 245155 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.3926. Min Act: -0.0001

Data Index: 477798 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.3162. Min Act: -0.0001

Data Index: 637755 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.3883. Min Act: -0.0001

Data Index: 1316649 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.2989. Min Act: -0.0001

Data Index: 1037811 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.3725. Min Act: -0.0001

Data Index: 769703 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.3598. Min Act: -0.0001

Data Index: 411570 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.1371. Min Act: -0.0001

Data Index: 1277256 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.1211. Min Act: -0.0001

Data Index: 436733 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.1418. Min Act: -0.0001

Data Index: 977274 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0305. Min Act: -0.0001

Data Index: 49170 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.1125. Min Act: -0.0001

Data Index: 1022148 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9832. Min Act: -0.0001

Data Index: 116048 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0277. Min Act: -0.0001

Data Index: 1167646 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 1.5186. Min Range: -1.5186

Max Act: 0.9976. Min Act: -0.0001

Data Index: 153462 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.5186. Min Range: -1.5186

Max Act: 1.0607. Min Act: -0.0001

Data Index: 48694 (C4 (Web Text))

Max Activating Token Index: 18