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

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

Neuron 4793 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4520. Min Range: -6.4520

Max Act: 6.1421. Min Act: -0.0001

Data Index: 142508 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 6.4520. Min Range: -6.4520

Max Act: 6.4520. Min Act: -0.0000

Data Index: 239763 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.7832. Min Act: -0.0001

Data Index: 1157412 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 6.4520. Min Range: -6.4520

Max Act: 6.1579. Min Act: -0.0001

Data Index: 1275189 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 6.4520. Min Range: -6.4520

Max Act: 6.1013. Min Act: -0.0000

Data Index: 404495 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 6.4520. Min Range: -6.4520

Max Act: 6.0728. Min Act: -0.0001

Data Index: 964231 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.6755. Min Act: -0.0001

Data Index: 161046 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.6464. Min Act: -0.0001

Data Index: 353788 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.6907. Min Act: -0.0001

Data Index: 682072 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.6290. Min Act: -0.0000

Data Index: 1423128 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.4079. Min Act: -0.0000

Data Index: 1608627 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.1308. Min Act: -0.0000

Data Index: 309142 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 6.4520. Min Range: -6.4520

Max Act: 4.9519. Min Act: -0.0001

Data Index: 1158717 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.1198. Min Act: -0.0000

Data Index: 225472 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.6016. Min Act: -0.0001

Data Index: 41048 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.2377. Min Act: -0.0000

Data Index: 1031521 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.2490. Min Act: -0.0000

Data Index: 1214225 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 6.4520. Min Range: -6.4520

Max Act: 4.8042. Min Act: -0.0000

Data Index: 654653 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 6.4520. Min Range: -6.4520

Max Act: 4.9623. Min Act: -0.0001

Data Index: 976687 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 6.4520. Min Range: -6.4520

Max Act: 5.0960. Min Act: -0.0000

Data Index: 288255 (C4 (Web Text))

Max Activating Token Index: 893