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

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

Neuron 2422 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0059. Min Range: -3.0059

Max Act: 3.0059. Min Act: -0.0000

Data Index: 1333832 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.9756. Min Act: -0.0000

Data Index: 57622 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.5656. Min Act: -0.0000

Data Index: 770367 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.6823. Min Act: -0.0000

Data Index: 941005 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.4052. Min Act: -0.0000

Data Index: 216527 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.5030. Min Act: -0.0000

Data Index: 937235 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.3854. Min Act: -0.0000

Data Index: 323450 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.3544. Min Act: -0.0000

Data Index: 604431 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.4546. Min Act: -0.0000

Data Index: 1303119 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.4440. Min Act: -0.0000

Data Index: 1349455 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.0597. Min Act: -0.0000

Data Index: 896497 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.3640. Min Act: -0.0000

Data Index: 301825 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.2412. Min Act: -0.0000

Data Index: 1134896 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.4526. Min Act: -0.0000

Data Index: 316809 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.3277. Min Act: -0.0001

Data Index: 1293682 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.3002. Min Act: -0.0001

Data Index: 1274589 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.3037. Min Act: -0.0000

Data Index: 236487 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.2886. Min Act: -0.0001

Data Index: 1232417 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.2673. Min Act: -0.0000

Data Index: 662815 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 3.0059. Min Range: -3.0059

Max Act: 2.3817. Min Act: -0.0000

Data Index: 562772 (C4 (Web Text))

Max Activating Token Index: 373