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

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

Neuron 5669 in Layer 0

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: 0.5419. Min Range: -0.5419

Max Act: 0.5419. Min Act: -0.0001

Data Index: 470261 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4943. Min Act: -0.0001

Data Index: 287232 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4785. Min Act: -0.0001

Data Index: 1203852 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4708. Min Act: -0.0001

Data Index: 154747 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4476. Min Act: -0.0001

Data Index: 469716 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4470. Min Act: -0.0001

Data Index: 1214507 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4361. Min Act: -0.0001

Data Index: 1257405 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4419. Min Act: -0.0001

Data Index: 1350253 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4373. Min Act: -0.0001

Data Index: 493604 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4345. Min Act: -0.0001

Data Index: 814492 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4212. Min Act: -0.0001

Data Index: 101697 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4264. Min Act: -0.0001

Data Index: 218465 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4263. Min Act: -0.0002

Data Index: 1321507 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4189. Min Act: -0.0001

Data Index: 1116347 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4225. Min Act: -0.0001

Data Index: 893066 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4119. Min Act: -0.0001

Data Index: 1067001 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4172. Min Act: -0.0001

Data Index: 915502 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4098. Min Act: -0.0001

Data Index: 826704 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4045. Min Act: -0.0001

Data Index: 199265 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.5419. Min Range: -0.5419

Max Act: 0.4115. Min Act: -0.0001

Data Index: 1154936 (C4 (Web Text))

Max Activating Token Index: 880