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

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

Neuron 2157 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0003

Data Index: 926749 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0112. Min Act: -0.0002

Data Index: 694057 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0100. Min Act: -0.0003

Data Index: 1189311 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0077. Min Act: -0.0003

Data Index: 175667 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0077. Min Act: -0.0003

Data Index: 170549 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0074. Min Act: -0.0003

Data Index: 469982 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0073. Min Act: -0.0003

Data Index: 922374 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1238676 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1212440 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0050. Min Act: -0.0002

Data Index: 332129 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0051. Min Act: -0.0003

Data Index: 758393 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0048. Min Act: -0.0003

Data Index: 762570 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1163795 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1102230 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0046. Min Act: -0.0002

Data Index: 425792 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0045. Min Act: -0.0003

Data Index: 415778 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1259386 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0043. Min Act: -0.0003

Data Index: 478805 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0044. Min Act: -0.0003

Data Index: 698635 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0044. Min Act: -0.0002

Data Index: 318687 (C4 (Web Text))

Max Activating Token Index: 718