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

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

Neuron 4805 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: 1.0423. Min Range: -1.0423

Max Act: 1.0423. Min Act: -0.0003

Data Index: 438235 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9899. Min Act: -0.0002

Data Index: 858382 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.0423. Min Range: -1.0423

Max Act: 1.0030. Min Act: -0.0002

Data Index: 911486 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9798. Min Act: -0.0002

Data Index: 311054 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9742. Min Act: -0.0002

Data Index: 257098 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9688. Min Act: -0.0003

Data Index: 709121 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9581. Min Act: -0.0002

Data Index: 157143 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9526. Min Act: -0.0002

Data Index: 880336 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9450. Min Act: -0.0002

Data Index: 1306556 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9211. Min Act: -0.0003

Data Index: 1192660 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9323. Min Act: -0.0002

Data Index: 190224 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9229. Min Act: -0.0002

Data Index: 631882 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9479. Min Act: -0.0002

Data Index: 932832 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9203. Min Act: -0.0002

Data Index: 182178 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9368. Min Act: -0.0002

Data Index: 1281842 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9174. Min Act: -0.0002

Data Index: 460154 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9317. Min Act: -0.0002

Data Index: 577011 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9325. Min Act: -0.0002

Data Index: 1178010 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9139. Min Act: -0.0002

Data Index: 775212 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 1.0423. Min Range: -1.0423

Max Act: 0.9113. Min Act: -0.0002

Data Index: 126633 (C4 (Web Text))

Max Activating Token Index: 519