Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3428 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.8877. Min Act: -0.0000

Data Index: 798560 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.9140. Min Act: -0.0000

Data Index: 297274 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.8674. Min Act: -0.0000

Data Index: 900299 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.8290. Min Act: -0.0000

Data Index: 514280 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1234788 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1088387 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1588971 (Python Code)

Max Activating Token Index: 688

Text #7

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.7240. Min Act: -0.0000

Data Index: 187742 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.7408. Min Act: -0.0000

Data Index: 721453 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.7178. Min Act: -0.0000

Data Index: 538558 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6672. Min Act: -0.0000

Data Index: 151221 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6827. Min Act: -0.0000

Data Index: 566720 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1171809 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6979. Min Act: -0.0000

Data Index: 266158 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6923. Min Act: -0.0000

Data Index: 225612 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6288. Min Act: -0.0000

Data Index: 241411 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6557. Min Act: -0.0000

Data Index: 489305 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6480. Min Act: -0.0000

Data Index: 1317205 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.6248. Min Act: -0.0000

Data Index: 607950 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.9140. Min Range: -0.9140

Max Act: 0.5999. Min Act: -0.0000

Data Index: 87818 (C4 (Web Text))

Max Activating Token Index: 154