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

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

Neuron 1960 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3343. Min Range: -6.3343

Max Act: 6.1487. Min Act: 0.0000

Data Index: 252681 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 6.3343. Min Range: -6.3343

Max Act: 6.3343. Min Act: -0.0000

Data Index: 473852 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 6.3343. Min Range: -6.3343

Max Act: 5.7832. Min Act: -0.0001

Data Index: 81193 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 6.3343. Min Range: -6.3343

Max Act: 5.9129. Min Act: -0.0000

Data Index: 300195 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 6.3343. Min Range: -6.3343

Max Act: 5.1559. Min Act: -0.0001

Data Index: 476641 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 6.3343. Min Range: -6.3343

Max Act: 5.1099. Min Act: -0.0001

Data Index: 642331 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 6.3343. Min Range: -6.3343

Max Act: 5.2237. Min Act: -0.0001

Data Index: 1005288 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.7052. Min Act: -0.0001

Data Index: 1110000 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.6738. Min Act: -0.0001

Data Index: 466047 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.7005. Min Act: -0.0001

Data Index: 886707 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 6.3343. Min Range: -6.3343

Max Act: 3.1457. Min Act: -0.0000

Data Index: 747914 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.1038. Min Act: 0.0000

Data Index: 1333345 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.7206. Min Act: -0.0001

Data Index: 240376 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.2841. Min Act: -0.0000

Data Index: 1321583 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.4486. Min Act: -0.0000

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.0667. Min Act: -0.0001

Data Index: 932127 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.5494. Min Act: -0.0001

Data Index: 728148 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 6.3343. Min Range: -6.3343

Max Act: 3.6764. Min Act: -0.0001

Data Index: 738987 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 6.3343. Min Range: -6.3343

Max Act: 4.4936. Min Act: -0.0001

Data Index: 1063555 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 6.3343. Min Range: -6.3343

Max Act: 3.4505. Min Act: -0.0000

Data Index: 1259241 (C4 (Web Text))

Max Activating Token Index: 826