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

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

Neuron 77 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.1115. Min Act: -0.0001

Data Index: 233393 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1310997 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.1042. Min Act: -0.0000

Data Index: 19363 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.1070. Min Act: -0.0000

Data Index: 579100 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.1021. Min Act: -0.0001

Data Index: 678058 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0991. Min Act: -0.0001

Data Index: 681759 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0920. Min Act: -0.0001

Data Index: 770007 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.1002. Min Act: -0.0000

Data Index: 875138 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0912. Min Act: -0.0000

Data Index: 205106 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0925. Min Act: -0.0000

Data Index: 923232 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0924. Min Act: -0.0000

Data Index: 133865 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1347897 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1544 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0968. Min Act: -0.0001

Data Index: 567279 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0866. Min Act: -0.0000

Data Index: 500098 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0920. Min Act: -0.0000

Data Index: 943066 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0915. Min Act: -0.0000

Data Index: 534866 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0854. Min Act: -0.0000

Data Index: 513707 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0916. Min Act: -0.0000

Data Index: 778871 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.1115. Min Range: -0.1115

Max Act: 0.0845. Min Act: -0.0001

Data Index: 353928 (C4 (Web Text))

Max Activating Token Index: 306