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

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

Neuron 659 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.5360. Min Act: -0.0000

Data Index: 842643 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.5068. Min Act: -0.0000

Data Index: 189734 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4799. Min Act: -0.0000

Data Index: 300931 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.5041. Min Act: -0.0000

Data Index: 872651 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4999. Min Act: -0.0000

Data Index: 468453 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4907. Min Act: -0.0000

Data Index: 452786 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4869. Min Act: -0.0000

Data Index: 146064 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4774. Min Act: -0.0000

Data Index: 462706 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4868. Min Act: -0.0000

Data Index: 982468 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4563. Min Act: -0.0000

Data Index: 478486 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4707. Min Act: -0.0000

Data Index: 146353 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4337. Min Act: -0.0000

Data Index: 258576 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1331507 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1002659 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4549. Min Act: -0.0000

Data Index: 633571 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4347. Min Act: -0.0000

Data Index: 750260 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1116209 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4244. Min Act: -0.0000

Data Index: 465270 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4005. Min Act: -0.0000

Data Index: 868016 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 0.5360. Min Range: -0.5360

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1097882 (C4 (Web Text))

Max Activating Token Index: 265