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

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

Neuron 643 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: 2.0086. Min Range: -2.0086

Max Act: 2.0086. Min Act: -0.0002

Data Index: 347612 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.9610. Min Act: -0.0002

Data Index: 800389 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.9289. Min Act: -0.0002

Data Index: 133300 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.8404. Min Act: -0.0002

Data Index: 845252 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.8522. Min Act: -0.0002

Data Index: 1183392 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.8356. Min Act: -0.0002

Data Index: 805712 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.8237. Min Act: -0.0002

Data Index: 403120 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.7764. Min Act: -0.0002

Data Index: 1017923 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.7523. Min Act: -0.0002

Data Index: 1200322 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.7537. Min Act: -0.0002

Data Index: 450171 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.7264. Min Act: -0.0002

Data Index: 157585 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.7403. Min Act: -0.0002

Data Index: 878723 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.7033. Min Act: -0.0002

Data Index: 159257 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.6925. Min Act: -0.0002

Data Index: 596231 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.7258. Min Act: -0.0002

Data Index: 1287024 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.7249. Min Act: -0.0002

Data Index: 1021506 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.6883. Min Act: -0.0002

Data Index: 1133492 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.7120. Min Act: -0.0002

Data Index: 1112410 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.6864. Min Act: -0.0002

Data Index: 294664 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 2.0086. Min Range: -2.0086

Max Act: 1.6748. Min Act: -0.0002

Data Index: 957611 (C4 (Web Text))

Max Activating Token Index: 324