Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 685 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3318. Min Act: -0.0006

Data Index: 435116 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2831. Min Act: -0.0006

Data Index: 922802 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3264. Min Act: -0.0006

Data Index: 744080 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3144. Min Act: -0.0006

Data Index: 213657 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3100. Min Act: -0.0006

Data Index: 952683 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2988. Min Act: -0.0006

Data Index: 434710 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3060. Min Act: -0.0006

Data Index: 807799 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3014. Min Act: -0.0006

Data Index: 1334026 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2828. Min Act: -0.0006

Data Index: 1284732 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.3024. Min Act: -0.0006

Data Index: 1188209 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2786. Min Act: -0.0006

Data Index: 939526 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2673. Min Act: -0.0006

Data Index: 108475 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2411. Min Act: -0.0006

Data Index: 122570 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2284. Min Act: -0.0006

Data Index: 1109802 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2832. Min Act: -0.0006

Data Index: 232487 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2428. Min Act: -0.0006

Data Index: 576299 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2412. Min Act: -0.0006

Data Index: 421600 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2443. Min Act: -0.0006

Data Index: 335709 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2605. Min Act: -0.0006

Data Index: 82362 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.3318. Min Range: -0.3318

Max Act: 0.2334. Min Act: -0.0006

Data Index: 468335 (C4 (Web Text))

Max Activating Token Index: 584