Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2945 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.2939. Min Act: -0.0002

Data Index: 2246 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.1758. Min Act: -0.0002

Data Index: 367460 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.1960. Min Act: -0.0002

Data Index: 270621 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.1485. Min Act: -0.0002

Data Index: 1153138 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.1275. Min Act: -0.0002

Data Index: 827829 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.1432. Min Act: -0.0002

Data Index: 559966 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0995. Min Act: -0.0002

Data Index: 1357910 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0865. Min Act: -0.0002

Data Index: 559864 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.1034. Min Act: -0.0002

Data Index: 164302 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0839. Min Act: -0.0002

Data Index: 115725 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0693. Min Act: -0.0002

Data Index: 444391 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.1218. Min Act: -0.0002

Data Index: 630433 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0676. Min Act: -0.0002

Data Index: 1209116 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0479. Min Act: -0.0002

Data Index: 175214 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0516. Min Act: -0.0002

Data Index: 677475 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0830. Min Act: -0.0002

Data Index: 1127087 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0722. Min Act: -0.0002

Data Index: 760196 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0477. Min Act: -0.0002

Data Index: 796365 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0537. Min Act: -0.0002

Data Index: 913304 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 1.2939. Min Range: -1.2939

Max Act: 1.0459. Min Act: -0.0002

Data Index: 1112869 (C4 (Web Text))

Max Activating Token Index: 774