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

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

Neuron 4397 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8349. Min Range: -7.8349

Max Act: 7.8349. Min Act: -0.0001

Data Index: 1320402 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 7.8349. Min Range: -7.8349

Max Act: 5.3121. Min Act: -0.0001

Data Index: 623901 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.8178. Min Act: -0.0001

Data Index: 620727 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.8726. Min Act: -0.0001

Data Index: 1308725 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 7.8349. Min Range: -7.8349

Max Act: 5.0769. Min Act: -0.0001

Data Index: 389272 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.4382. Min Act: -0.0001

Data Index: 381787 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.6203. Min Act: -0.0001

Data Index: 1355806 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.7848. Min Act: -0.0001

Data Index: 44190 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.4416. Min Act: -0.0001

Data Index: 1297021 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.6079. Min Act: -0.0001

Data Index: 241632 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.8372. Min Act: -0.0001

Data Index: 1005293 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.5459. Min Act: -0.0001

Data Index: 888892 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.1545. Min Act: -0.0001

Data Index: 212774 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.6382. Min Act: -0.0001

Data Index: 106189 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.0021. Min Act: -0.0001

Data Index: 495011 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.3187. Min Act: -0.0001

Data Index: 710908 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.5398. Min Act: -0.0001

Data Index: 316688 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 7.8349. Min Range: -7.8349

Max Act: 4.0159. Min Act: -0.0001

Data Index: 571477 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 7.8349. Min Range: -7.8349

Max Act: 3.5738. Min Act: -0.0001

Data Index: 1310411 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 7.8349. Min Range: -7.8349

Max Act: 3.7142. Min Act: -0.0001

Data Index: 554323 (C4 (Web Text))

Max Activating Token Index: 510