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

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

Neuron 3102 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.5906. Min Act: -0.0000

Data Index: 931937 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.4169. Min Act: -0.0000

Data Index: 636661 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.5163. Min Act: -0.0000

Data Index: 299192 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1353383 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3969. Min Act: -0.0000

Data Index: 557500 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.4030. Min Act: -0.0000

Data Index: 670432 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.3275. Min Act: -0.0000

Data Index: 1026096 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2864. Min Act: -0.0000

Data Index: 1307767 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2380. Min Act: -0.0000

Data Index: 1309159 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1203328 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1803. Min Act: -0.0001

Data Index: 426046 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.2802. Min Act: -0.0001

Data Index: 653765 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1361. Min Act: -0.0001

Data Index: 619351 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.0934. Min Act: -0.0000

Data Index: 203118 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.0602. Min Act: -0.0001

Data Index: 25493 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1265799 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1789. Min Act: -0.0000

Data Index: 460489 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.1265. Min Act: -0.0001

Data Index: 360998 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.0469. Min Act: -0.0000

Data Index: 906548 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 1.5906. Min Range: -1.5906

Max Act: 1.0344. Min Act: -0.0000

Data Index: 494689 (C4 (Web Text))

Max Activating Token Index: 749