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

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

Neuron 664 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2162. Min Range: -2.2162

Max Act: 2.2162. Min Act: -0.0000

Data Index: 82198 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.8816. Min Act: -0.0000

Data Index: 958313 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 2.2162. Min Range: -2.2162

Max Act: 2.0107. Min Act: -0.0000

Data Index: 1229221 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1234742 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.5731. Min Act: -0.0000

Data Index: 933259 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.5594. Min Act: -0.0000

Data Index: 1353012 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.6038. Min Act: -0.0000

Data Index: 316918 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.3981. Min Act: -0.0000

Data Index: 350629 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.6550. Min Act: -0.0000

Data Index: 132669 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.3718. Min Act: -0.0000

Data Index: 928534 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.3494. Min Act: -0.0000

Data Index: 1287211 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.4074. Min Act: -0.0000

Data Index: 36794 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.4739. Min Act: -0.0000

Data Index: 975425 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.3867. Min Act: -0.0000

Data Index: 944553 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.3853. Min Act: -0.0000

Data Index: 573354 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.4546. Min Act: -0.0000

Data Index: 700668 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1032930 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.2686. Min Act: -0.0000

Data Index: 40098 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.4078. Min Act: -0.0000

Data Index: 471897 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 2.2162. Min Range: -2.2162

Max Act: 1.3295. Min Act: -0.0000

Data Index: 742233 (C4 (Web Text))

Max Activating Token Index: 700