Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3396 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1232. Min Range: -1.1232

Max Act: 1.1232. Min Act: -0.0001

Data Index: 753557 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.1232. Min Range: -1.1232

Max Act: 1.0563. Min Act: -0.0001

Data Index: 660269 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9067. Min Act: -0.0001

Data Index: 93453 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 1.1232. Min Range: -1.1232

Max Act: 1.0158. Min Act: -0.0001

Data Index: 508781 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8915. Min Act: -0.0001

Data Index: 1148246 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.9027. Min Act: -0.0001

Data Index: 892814 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8330. Min Act: -0.0001

Data Index: 1005562 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7281. Min Act: -0.0001

Data Index: 1193269 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7955. Min Act: -0.0001

Data Index: 721358 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8110. Min Act: -0.0001

Data Index: 295021 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.8597. Min Act: -0.0001

Data Index: 1201441 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7457. Min Act: -0.0001

Data Index: 541997 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7323. Min Act: -0.0001

Data Index: 998566 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7315. Min Act: -0.0001

Data Index: 313937 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7546. Min Act: -0.0001

Data Index: 176528 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7129. Min Act: -0.0001

Data Index: 488530 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7287. Min Act: -0.0001

Data Index: 637521 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.7051. Min Act: -0.0001

Data Index: 1197027 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6721. Min Act: -0.0001

Data Index: 136718 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 1.1232. Min Range: -1.1232

Max Act: 0.6462. Min Act: -0.0001

Data Index: 554573 (C4 (Web Text))

Max Activating Token Index: 441