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

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

Neuron 3424 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: 1.9069. Min Range: -1.9069

Max Act: 1.9069. Min Act: -0.0003

Data Index: 201367 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6989. Min Act: -0.0002

Data Index: 1336150 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.7369. Min Act: -0.0002

Data Index: 773311 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6871. Min Act: -0.0003

Data Index: 196349 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6537. Min Act: -0.0002

Data Index: 1145937 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6408. Min Act: -0.0002

Data Index: 1336730 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6230. Min Act: -0.0002

Data Index: 488243 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6392. Min Act: -0.0002

Data Index: 192761 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6104. Min Act: -0.0003

Data Index: 590408 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.5774. Min Act: -0.0002

Data Index: 949398 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.5987. Min Act: -0.0002

Data Index: 1035449 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6039. Min Act: -0.0002

Data Index: 1193468 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6300. Min Act: -0.0002

Data Index: 47884 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.6055. Min Act: -0.0003

Data Index: 841676 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.5968. Min Act: -0.0002

Data Index: 588804 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.5971. Min Act: -0.0003

Data Index: 1270976 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.5514. Min Act: -0.0002

Data Index: 809783 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.5761. Min Act: -0.0002

Data Index: 386595 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.5683. Min Act: -0.0002

Data Index: 1229557 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.9069. Min Range: -1.9069

Max Act: 1.5535. Min Act: -0.0002

Data Index: 686786 (C4 (Web Text))

Max Activating Token Index: 66