Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3972 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1038162 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1221171 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4423. Min Act: -0.0001

Data Index: 115258 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1206463 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4494. Min Act: -0.0000

Data Index: 737205 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4448. Min Act: -0.0001

Data Index: 108434 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4206. Min Act: -0.0001

Data Index: 1041763 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4283. Min Act: -0.0001

Data Index: 736011 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4106. Min Act: -0.0000

Data Index: 359755 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4384. Min Act: -0.0001

Data Index: 1167656 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4225. Min Act: -0.0001

Data Index: 827752 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4148. Min Act: -0.0000

Data Index: 643060 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1305539 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4250. Min Act: 0.0001

Data Index: 351813 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4086. Min Act: -0.0000

Data Index: 78800 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4180. Min Act: -0.0000

Data Index: 1065232 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4080. Min Act: -0.0001

Data Index: 695434 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3937. Min Act: -0.0000

Data Index: 45269 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.3927. Min Act: -0.0001

Data Index: 354845 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.4593. Min Range: -0.4593

Max Act: 0.4003. Min Act: -0.0000

Data Index: 337578 (C4 (Web Text))

Max Activating Token Index: 692