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

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

Neuron 5173 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.6134. Min Act: -0.0002

Data Index: 1249552 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5927. Min Act: -0.0002

Data Index: 555927 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5895. Min Act: -0.0002

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5852. Min Act: -0.0002

Data Index: 1085295 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5673. Min Act: -0.0002

Data Index: 44618 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5402. Min Act: -0.0002

Data Index: 1056033 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5202. Min Act: -0.0002

Data Index: 237082 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5227. Min Act: -0.0002

Data Index: 1195764 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5390. Min Act: -0.0002

Data Index: 653959 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5208. Min Act: -0.0002

Data Index: 480680 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5006. Min Act: -0.0002

Data Index: 842880 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5085. Min Act: -0.0002

Data Index: 1592765 (Python Code)

Max Activating Token Index: 207

Text #12

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4881. Min Act: -0.0002

Data Index: 1194808 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4715. Min Act: -0.0002

Data Index: 1276690 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4952. Min Act: -0.0002

Data Index: 673351 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4968. Min Act: -0.0002

Data Index: 361978 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4913. Min Act: -0.0002

Data Index: 315039 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5095. Min Act: -0.0002

Data Index: 374104 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4571. Min Act: -0.0002

Data Index: 1125277 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4894. Min Act: -0.0002

Data Index: 1280106 (C4 (Web Text))

Max Activating Token Index: 489