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

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

Neuron 2754 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: 2.3978. Min Range: -2.3978

Max Act: 2.3978. Min Act: -0.0000

Data Index: 109034 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 2.3978. Min Range: -2.3978

Max Act: 2.3978. Min Act: -0.0000

Data Index: 532267 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.9818. Min Act: -0.0000

Data Index: 1036874 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 2.3978. Min Range: -2.3978

Max Act: 2.0048. Min Act: -0.0000

Data Index: 407185 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.7119. Min Act: -0.0000

Data Index: 1299517 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.8572. Min Act: -0.0000

Data Index: 1238726 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.7326. Min Act: -0.0000

Data Index: 573670 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.6210. Min Act: -0.0000

Data Index: 1040583 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.7240. Min Act: -0.0000

Data Index: 646466 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1188397 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.6096. Min Act: -0.0000

Data Index: 280259 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1124834 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.5852. Min Act: -0.0000

Data Index: 37172 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.6701. Min Act: -0.0000

Data Index: 971506 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.6298. Min Act: -0.0000

Data Index: 162666 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.6966. Min Act: -0.0000

Data Index: 699317 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.5337. Min Act: -0.0000

Data Index: 901005 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1085415 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.5211. Min Act: -0.0000

Data Index: 362520 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 2.3978. Min Range: -2.3978

Max Act: 1.4524. Min Act: -0.0000

Data Index: 465191 (C4 (Web Text))

Max Activating Token Index: 181