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

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

Neuron 938 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: 2.8154. Min Range: -2.8154

Max Act: 2.8154. Min Act: -0.0000

Data Index: 1140036 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.5148. Min Act: -0.0000

Data Index: 381658 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.4822. Min Act: -0.0000

Data Index: 1247574 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.5455. Min Act: -0.0000

Data Index: 422911 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.5571. Min Act: -0.0000

Data Index: 576358 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.3193. Min Act: -0.0000

Data Index: 903692 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.1406. Min Act: -0.0000

Data Index: 165780 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.0850. Min Act: -0.0000

Data Index: 973187 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 2.8154. Min Range: -2.8154

Max Act: 2.0779. Min Act: -0.0000

Data Index: 190910 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.8547. Min Act: -0.0000

Data Index: 109311 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.9429. Min Act: -0.0000

Data Index: 1320042 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.9452. Min Act: -0.0000

Data Index: 714423 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.7625. Min Act: -0.0000

Data Index: 963526 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.9514. Min Act: -0.0000

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.8236. Min Act: -0.0000

Data Index: 590917 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.8742. Min Act: -0.0000

Data Index: 901995 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.8717. Min Act: -0.0000

Data Index: 1306889 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.7389. Min Act: -0.0000

Data Index: 675044 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.7182. Min Act: -0.0000

Data Index: 1316514 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 2.8154. Min Range: -2.8154

Max Act: 1.6010. Min Act: -0.0000

Data Index: 338902 (C4 (Web Text))

Max Activating Token Index: 733