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

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

Neuron 2669 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: 0.9476. Min Range: -0.9476

Max Act: 0.9476. Min Act: -0.0002

Data Index: 189120 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.8985. Min Act: -0.0002

Data Index: 467239 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.8559. Min Act: -0.0002

Data Index: 639676 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.8379. Min Act: -0.0002

Data Index: 751561 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.8455. Min Act: -0.0002

Data Index: 1470171 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.8167. Min Act: -0.0002

Data Index: 997168 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.8131. Min Act: -0.0002

Data Index: 1421533 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7835. Min Act: -0.0002

Data Index: 365617 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7965. Min Act: -0.0002

Data Index: 257643 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7849. Min Act: -0.0002

Data Index: 1314011 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7817. Min Act: -0.0002

Data Index: 541356 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7845. Min Act: -0.0002

Data Index: 201789 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7811. Min Act: -0.0002

Data Index: 1214511 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7606. Min Act: -0.0002

Data Index: 557102 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7532. Min Act: -0.0002

Data Index: 270108 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7680. Min Act: -0.0002

Data Index: 186069 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7451. Min Act: -0.0002

Data Index: 1299763 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7494. Min Act: -0.0002

Data Index: 3812 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7374. Min Act: -0.0002

Data Index: 1339425 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.9476. Min Range: -0.9476

Max Act: 0.7546. Min Act: -0.0002

Data Index: 942279 (C4 (Web Text))

Max Activating Token Index: 553