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

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

Neuron 1487 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1159. Min Act: -0.0001

Data Index: 446721 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1100. Min Act: -0.0001

Data Index: 191790 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1069. Min Act: -0.0001

Data Index: 812575 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1096353 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1041. Min Act: -0.0001

Data Index: 167041 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1473965 (Python Code)

Max Activating Token Index: 580

Text #6

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1536987 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1184550 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1468861 (Python Code)

Max Activating Token Index: 72

Text #9

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1454555 (Python Code)

Max Activating Token Index: 768

Text #10

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1505811 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1392428 (Python Code)

Max Activating Token Index: 430

Text #12

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0943. Min Act: -0.0001

Data Index: 1609587 (Python Code)

Max Activating Token Index: 470

Text #13

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0932. Min Act: -0.0001

Data Index: 907847 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0965. Min Act: -0.0001

Data Index: 161119 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1038516 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0888. Min Act: -0.0001

Data Index: 341874 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0850. Min Act: -0.0001

Data Index: 68717 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0899. Min Act: -0.0001

Data Index: 814184 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0912. Min Act: -0.0001

Data Index: 913845 (C4 (Web Text))

Max Activating Token Index: 721