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

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

Neuron 1559 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.4847. Min Act: -0.0000

Data Index: 1290799 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.2950. Min Act: -0.0001

Data Index: 892499 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.2276. Min Act: -0.0000

Data Index: 67920 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.2109. Min Act: -0.0001

Data Index: 331063 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.1688. Min Act: -0.0000

Data Index: 483193 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.1794. Min Act: -0.0001

Data Index: 683776 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.0444. Min Act: -0.0001

Data Index: 1014878 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.0556. Min Act: -0.0000

Data Index: 735747 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.0614. Min Act: -0.0001

Data Index: 530870 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.0375. Min Act: -0.0000

Data Index: 774531 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.0287. Min Act: -0.0001

Data Index: 368761 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.4847. Min Range: -1.4847

Max Act: 0.9905. Min Act: -0.0001

Data Index: 78613 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.0138. Min Act: -0.0001

Data Index: 77032 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1002790 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.4847. Min Range: -1.4847

Max Act: 1.0589. Min Act: -0.0001

Data Index: 25601 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 1.4847. Min Range: -1.4847

Max Act: 0.9724. Min Act: -0.0001

Data Index: 156764 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.4847. Min Range: -1.4847

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1288934 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.4847. Min Range: -1.4847

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1102043 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.4847. Min Range: -1.4847

Max Act: 0.9646. Min Act: -0.0001

Data Index: 38464 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 1.4847. Min Range: -1.4847

Max Act: 0.9105. Min Act: -0.0001

Data Index: 388715 (C4 (Web Text))

Max Activating Token Index: 407