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

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

Neuron 567 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5032. Min Act: -0.0003

Data Index: 857771 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5443. Min Act: -0.0003

Data Index: 909190 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4108. Min Act: -0.0003

Data Index: 62609 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5241. Min Act: -0.0003

Data Index: 347092 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4618. Min Act: -0.0003

Data Index: 1036830 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4551. Min Act: -0.0003

Data Index: 427217 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5129. Min Act: -0.0003

Data Index: 680699 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4650. Min Act: -0.0003

Data Index: 1188292 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4313. Min Act: -0.0003

Data Index: 662385 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4602. Min Act: -0.0003

Data Index: 245767 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.5070. Min Act: -0.0003

Data Index: 909100 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4286. Min Act: -0.0003

Data Index: 32597 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4430. Min Act: -0.0003

Data Index: 718020 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4546. Min Act: -0.0003

Data Index: 423197 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4668. Min Act: -0.0003

Data Index: 397170 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4748. Min Act: -0.0003

Data Index: 814226 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4307. Min Act: -0.0003

Data Index: 50781 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4272. Min Act: -0.0003

Data Index: 702794 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.3718. Min Act: -0.0003

Data Index: 163086 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.5443. Min Range: -0.5443

Max Act: 0.4544. Min Act: -0.0003

Data Index: 562674 (C4 (Web Text))

Max Activating Token Index: 361