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

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

Neuron 3724 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6544. Min Range: -1.6544

Max Act: 1.6544. Min Act: -0.0000

Data Index: 484295 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.6544. Min Range: -1.6544

Max Act: 1.2417. Min Act: -0.0000

Data Index: 50325 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.6544. Min Range: -1.6544

Max Act: 1.1061. Min Act: -0.0000

Data Index: 309296 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.9854. Min Act: -0.0000

Data Index: 84108 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.9697. Min Act: -0.0000

Data Index: 117123 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.9702. Min Act: -0.0000

Data Index: 154431 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.9922. Min Act: -0.0000

Data Index: 948520 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.8473. Min Act: -0.0000

Data Index: 394647 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.8529. Min Act: -0.0000

Data Index: 350484 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.9054. Min Act: -0.0000

Data Index: 59908 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.8932. Min Act: -0.0000

Data Index: 147695 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.8717. Min Act: -0.0000

Data Index: 475591 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.8763. Min Act: -0.0000

Data Index: 879567 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.9246. Min Act: -0.0000

Data Index: 841311 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1267442 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.8964. Min Act: -0.0000

Data Index: 213605 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1349420 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.7710. Min Act: -0.0000

Data Index: 746280 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.7207. Min Act: -0.0000

Data Index: 89438 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.6544. Min Range: -1.6544

Max Act: 0.7225. Min Act: -0.0000

Data Index: 579055 (C4 (Web Text))

Max Activating Token Index: 894