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

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

Neuron 304 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: 0.5304. Min Range: -0.5304

Max Act: 0.5304. Min Act: -0.0002

Data Index: 646631 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.5147. Min Act: -0.0002

Data Index: 899727 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4903. Min Act: -0.0002

Data Index: 653432 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4786. Min Act: -0.0002

Data Index: 1289197 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4699. Min Act: -0.0002

Data Index: 343049 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4801. Min Act: -0.0002

Data Index: 514212 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4517. Min Act: -0.0002

Data Index: 907468 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4515. Min Act: -0.0002

Data Index: 884763 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4486. Min Act: -0.0002

Data Index: 900435 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4365. Min Act: -0.0002

Data Index: 960736 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4350. Min Act: -0.0002

Data Index: 77064 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4401. Min Act: -0.0002

Data Index: 75518 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4304. Min Act: -0.0002

Data Index: 745025 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4306. Min Act: -0.0002

Data Index: 311823 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4221. Min Act: -0.0002

Data Index: 1226728 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4215. Min Act: -0.0002

Data Index: 972534 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4080. Min Act: -0.0003

Data Index: 224690 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4169. Min Act: -0.0002

Data Index: 90941 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4128. Min Act: -0.0002

Data Index: 819157 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.5304. Min Range: -0.5304

Max Act: 0.4057. Min Act: -0.0002

Data Index: 1112819 (C4 (Web Text))

Max Activating Token Index: 551