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

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

Neuron 740 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.1288. Min Act: -0.0001

Data Index: 868845 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.1035. Min Act: -0.0001

Data Index: 437436 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.1288. Min Range: -1.1288

Max Act: 1.0812. Min Act: -0.0001

Data Index: 674905 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9883. Min Act: -0.0001

Data Index: 256807 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9881. Min Act: -0.0001

Data Index: 632448 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9513. Min Act: -0.0001

Data Index: 449561 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9228. Min Act: -0.0001

Data Index: 472983 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9209. Min Act: -0.0001

Data Index: 101905 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9437. Min Act: -0.0001

Data Index: 569466 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8834. Min Act: -0.0001

Data Index: 1316326 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8708. Min Act: -0.0001

Data Index: 1333516 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8831. Min Act: -0.0001

Data Index: 512169 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.9084. Min Act: -0.0001

Data Index: 1083861 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8774. Min Act: -0.0001

Data Index: 1150094 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8393. Min Act: -0.0001

Data Index: 841477 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8559. Min Act: -0.0001

Data Index: 917171 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8307. Min Act: -0.0001

Data Index: 1194561 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8787. Min Act: -0.0001

Data Index: 1195355 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8721. Min Act: -0.0001

Data Index: 200003 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.1288. Min Range: -1.1288

Max Act: 0.8929. Min Act: -0.0001

Data Index: 1357929 (C4 (Web Text))

Max Activating Token Index: 643