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

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

Neuron 665 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: 1.9682. Min Range: -1.9682

Max Act: 1.9637. Min Act: -0.0002

Data Index: 917666 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.9682. Min Act: -0.0002

Data Index: 238554 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.9107. Min Act: -0.0002

Data Index: 376867 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.8529. Min Act: -0.0002

Data Index: 131991 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.9287. Min Act: -0.0002

Data Index: 54582 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.8566. Min Act: -0.0002

Data Index: 1342310 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.7743. Min Act: -0.0002

Data Index: 649544 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.8266. Min Act: -0.0002

Data Index: 946627 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.7671. Min Act: -0.0002

Data Index: 1075277 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.7615. Min Act: -0.0002

Data Index: 1200679 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.7217. Min Act: -0.0002

Data Index: 99342 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.7633. Min Act: -0.0002

Data Index: 109456 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.6928. Min Act: -0.0002

Data Index: 850193 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.6375. Min Act: -0.0002

Data Index: 405127 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.6582. Min Act: -0.0002

Data Index: 961427 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.6361. Min Act: -0.0002

Data Index: 607837 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.6389. Min Act: -0.0002

Data Index: 619120 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.6462. Min Act: -0.0002

Data Index: 231309 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.5878. Min Act: -0.0002

Data Index: 1317592 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.9682. Min Range: -1.9682

Max Act: 1.6204. Min Act: -0.0002

Data Index: 730999 (C4 (Web Text))

Max Activating Token Index: 559