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

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

Neuron 23 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.7605. Min Act: -0.0000

Data Index: 89716 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.4461. Min Act: -0.0000

Data Index: 922164 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.5367. Min Act: -0.0000

Data Index: 1295711 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.3806. Min Act: -0.0000

Data Index: 918110 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.3487. Min Act: -0.0000

Data Index: 288785 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.4524. Min Act: 0.0000

Data Index: 609661 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.2893. Min Act: -0.0000

Data Index: 777379 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.2711. Min Act: -0.0000

Data Index: 907694 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.3937. Min Act: -0.0000

Data Index: 603087 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.1448. Min Act: 0.0000

Data Index: 3354 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.2310. Min Act: -0.0000

Data Index: 21314 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.2356. Min Act: -0.0000

Data Index: 726465 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.3578. Min Act: -0.0000

Data Index: 147558 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.2385. Min Act: -0.0000

Data Index: 88175 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.2013. Min Act: -0.0000

Data Index: 1255730 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.0986. Min Act: -0.0000

Data Index: 83774 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.3261. Min Act: -0.0000

Data Index: 838190 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.0678. Min Act: -0.0000

Data Index: 941664 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.1622. Min Act: -0.0000

Data Index: 1007251 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 2.7605. Min Range: -2.7605

Max Act: 2.0361. Min Act: -0.0000

Data Index: 1152935 (C4 (Web Text))

Max Activating Token Index: 915