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

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

Neuron 2101 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: 0.9254. Min Range: -0.9254

Max Act: 0.9254. Min Act: -0.0000

Data Index: 486489 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.9032. Min Act: -0.0000

Data Index: 819851 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.8428. Min Act: -0.0000

Data Index: 698143 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.8063. Min Act: -0.0000

Data Index: 572974 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7561. Min Act: -0.0000

Data Index: 147946 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7508. Min Act: -0.0000

Data Index: 195143 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1059688 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.8303. Min Act: -0.0000

Data Index: 275767 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7208. Min Act: -0.0000

Data Index: 492417 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7373. Min Act: -0.0000

Data Index: 508248 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7931. Min Act: -0.0000

Data Index: 386218 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7280. Min Act: -0.0000

Data Index: 530091 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1551875 (Python Code)

Max Activating Token Index: 160

Text #13

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6607. Min Act: -0.0000

Data Index: 642227 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7107. Min Act: -0.0000

Data Index: 711790 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6971. Min Act: -0.0000

Data Index: 46784 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.7272. Min Act: -0.0000

Data Index: 43258 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6814. Min Act: -0.0000

Data Index: 66083 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1418440 (Python Code)

Max Activating Token Index: 612

Text #19

Max Range: 0.9254. Min Range: -0.9254

Max Act: 0.5853. Min Act: -0.0000

Data Index: 874589 (C4 (Web Text))

Max Activating Token Index: 155