Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4471 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.4137. Min Act: -0.0000

Data Index: 1234429 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1055. Min Act: -0.0000

Data Index: 1191431 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1321. Min Act: -0.0000

Data Index: 297461 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.0495. Min Act: -0.0000

Data Index: 836787 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.0061. Min Act: -0.0000

Data Index: 348798 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.0037. Min Act: -0.0000

Data Index: 139826 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9671. Min Act: -0.0000

Data Index: 36991 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9069. Min Act: -0.0000

Data Index: 432016 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9501. Min Act: -0.0000

Data Index: 248441 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9312. Min Act: -0.0000

Data Index: 630078 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8906. Min Act: -0.0000

Data Index: 813829 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8675. Min Act: -0.0000

Data Index: 849064 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9075. Min Act: -0.0000

Data Index: 522996 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9082. Min Act: -0.0000

Data Index: 719258 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8920. Min Act: -0.0000

Data Index: 416739 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8621. Min Act: -0.0000

Data Index: 989021 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8933. Min Act: -0.0000

Data Index: 199427 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1294024 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8812. Min Act: -0.0000

Data Index: 772848 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8756. Min Act: -0.0000

Data Index: 595201 (C4 (Web Text))

Max Activating Token Index: 167