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

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

Neuron 3126 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.5166. Min Act: -0.0000

Data Index: 969474 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.3817. Min Act: -0.0000

Data Index: 160392 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.2639. Min Act: -0.0000

Data Index: 857064 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.2709. Min Act: -0.0000

Data Index: 1040182 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.1605. Min Act: -0.0000

Data Index: 1151233 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.2660. Min Act: -0.0000

Data Index: 689162 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.0311. Min Act: -0.0000

Data Index: 670237 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.0483. Min Act: -0.0000

Data Index: 1129519 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.0509. Min Act: -0.0000

Data Index: 458085 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.0851. Min Act: -0.0000

Data Index: 969790 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 2.5166. Min Range: -2.5166

Max Act: 1.9469. Min Act: -0.0000

Data Index: 565532 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.0403. Min Act: -0.0000

Data Index: 372073 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.0360. Min Act: -0.0000

Data Index: 136117 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 2.5166. Min Range: -2.5166

Max Act: 2.0439. Min Act: -0.0000

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 2.5166. Min Range: -2.5166

Max Act: 1.9186. Min Act: -0.0000

Data Index: 1213514 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 2.5166. Min Range: -2.5166

Max Act: 1.8986. Min Act: -0.0000

Data Index: 781548 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 2.5166. Min Range: -2.5166

Max Act: 1.7843. Min Act: -0.0000

Data Index: 955376 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 2.5166. Min Range: -2.5166

Max Act: 1.8764. Min Act: -0.0000

Data Index: 522383 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 2.5166. Min Range: -2.5166

Max Act: 1.8454. Min Act: -0.0000

Data Index: 514490 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 2.5166. Min Range: -2.5166

Max Act: 1.9542. Min Act: -0.0000

Data Index: 118548 (C4 (Web Text))

Max Activating Token Index: 605