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

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

Neuron 4198 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: 0.0486. Min Range: -0.0486

Max Act: 0.0486. Min Act: -0.0002

Data Index: 555709 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0415. Min Act: -0.0002

Data Index: 395144 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0318. Min Act: -0.0002

Data Index: 639513 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0321. Min Act: -0.0002

Data Index: 480877 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0307. Min Act: -0.0002

Data Index: 875593 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0305. Min Act: -0.0002

Data Index: 852205 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1358743 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0282. Min Act: -0.0002

Data Index: 59774 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0284. Min Act: -0.0002

Data Index: 532890 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0278. Min Act: -0.0002

Data Index: 174187 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0271. Min Act: -0.0002

Data Index: 157928 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0278. Min Act: -0.0002

Data Index: 221941 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0273. Min Act: -0.0002

Data Index: 449583 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1088299 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1280807 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0268. Min Act: -0.0002

Data Index: 224448 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1536748 (Python Code)

Max Activating Token Index: 50

Text #17

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0263. Min Act: -0.0002

Data Index: 945644 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0267. Min Act: -0.0002

Data Index: 101127 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0486. Min Range: -0.0486

Max Act: 0.0272. Min Act: -0.0002

Data Index: 211343 (C4 (Web Text))

Max Activating Token Index: 593