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

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

Neuron 4988 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: 1.1469. Min Range: -1.1469

Max Act: 1.1469. Min Act: -0.0002

Data Index: 757732 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.1469. Min Act: -0.0002

Data Index: 1026357 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0555. Min Act: -0.0002

Data Index: 92580 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0317. Min Act: -0.0002

Data Index: 429322 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0278. Min Act: -0.0002

Data Index: 991879 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0167. Min Act: -0.0002

Data Index: 1247026 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0069. Min Act: -0.0002

Data Index: 660723 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9866. Min Act: -0.0002

Data Index: 716796 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9901. Min Act: -0.0002

Data Index: 901935 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9816. Min Act: -0.0002

Data Index: 80757 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9681. Min Act: -0.0002

Data Index: 423634 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9461. Min Act: -0.0002

Data Index: 1323546 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9452. Min Act: -0.0002

Data Index: 1077597 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9391. Min Act: -0.0002

Data Index: 1156054 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9619. Min Act: -0.0002

Data Index: 43817 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9331. Min Act: -0.0002

Data Index: 355610 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9231. Min Act: -0.0002

Data Index: 891405 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9313. Min Act: -0.0002

Data Index: 390181 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9207. Min Act: -0.0002

Data Index: 378532 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 1.1469. Min Range: -1.1469

Max Act: 0.9169. Min Act: -0.0003

Data Index: 485030 (C4 (Web Text))

Max Activating Token Index: 773