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

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

Neuron 4800 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4987. Min Range: -3.4987

Max Act: 3.2579. Min Act: -0.0000

Data Index: 1270924 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.7833. Min Act: -0.0000

Data Index: 752877 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.3644. Min Act: -0.0000

Data Index: 231881 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.4555. Min Act: -0.0000

Data Index: 568168 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.6127. Min Act: -0.0000

Data Index: 36748 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 3.4987. Min Range: -3.4987

Max Act: 3.4987. Min Act: -0.0000

Data Index: 148657 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 3.4987. Min Range: -3.4987

Max Act: 3.0046. Min Act: -0.0000

Data Index: 1257291 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.9592. Min Act: -0.0000

Data Index: 422172 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.6200. Min Act: -0.0000

Data Index: 1246900 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.6028. Min Act: -0.0000

Data Index: 955365 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.6050. Min Act: -0.0000

Data Index: 590603 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.4673. Min Act: -0.0000

Data Index: 1123445 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.5609. Min Act: -0.0000

Data Index: 497741 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.0772. Min Act: -0.0000

Data Index: 1236237 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.6293. Min Act: -0.0000

Data Index: 555573 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.0053. Min Act: -0.0000

Data Index: 846192 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.4557. Min Act: -0.0000

Data Index: 1229519 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.5837. Min Act: -0.0000

Data Index: 1088518 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 3.4987. Min Range: -3.4987

Max Act: 1.7912. Min Act: -0.0000

Data Index: 1289789 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 3.4987. Min Range: -3.4987

Max Act: 2.3698. Min Act: -0.0000

Data Index: 934238 (C4 (Web Text))

Max Activating Token Index: 790