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

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

Neuron 307 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: 2.4221. Min Range: -2.4221

Max Act: 2.4221. Min Act: -0.0002

Data Index: 1574729 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 2.4221. Min Range: -2.4221

Max Act: 2.2502. Min Act: -0.0002

Data Index: 1585297 (Python Code)

Max Activating Token Index: 564

Text #2

Max Range: 2.4221. Min Range: -2.4221

Max Act: 2.0005. Min Act: -0.0002

Data Index: 1519351 (Python Code)

Max Activating Token Index: 719

Text #3

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.9770. Min Act: -0.0002

Data Index: 1511331 (Python Code)

Max Activating Token Index: 702

Text #4

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.9758. Min Act: -0.0002

Data Index: 1647957 (Python Code)

Max Activating Token Index: 630

Text #5

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.9503. Min Act: -0.0002

Data Index: 310405 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.9141. Min Act: -0.0002

Data Index: 270442 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.9820. Min Act: -0.0002

Data Index: 1638115 (Python Code)

Max Activating Token Index: 566

Text #8

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.8995. Min Act: -0.0002

Data Index: 4836 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.8872. Min Act: -0.0002

Data Index: 1493413 (Python Code)

Max Activating Token Index: 833

Text #10

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.8800. Min Act: -0.0002

Data Index: 1375405 (Python Code)

Max Activating Token Index: 819

Text #11

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.9226. Min Act: -0.0002

Data Index: 1135118 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.8704. Min Act: -0.0002

Data Index: 289968 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.8100. Min Act: -0.0002

Data Index: 1158261 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.7844. Min Act: -0.0002

Data Index: 1251476 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.8932. Min Act: -0.0002

Data Index: 1554164 (Python Code)

Max Activating Token Index: 917

Text #16

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.8565. Min Act: -0.0002

Data Index: 1612953 (Python Code)

Max Activating Token Index: 669

Text #17

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.8798. Min Act: -0.0002

Data Index: 1527281 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.7954. Min Act: -0.0002

Data Index: 911739 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 2.4221. Min Range: -2.4221

Max Act: 1.8321. Min Act: -0.0002

Data Index: 1096925 (C4 (Web Text))

Max Activating Token Index: 876