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

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

Neuron 6123 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2297. Min Range: -2.2297

Max Act: 2.2297. Min Act: -0.0000

Data Index: 958762 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.7899. Min Act: -0.0000

Data Index: 570371 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 2.2297. Min Range: -2.2297

Max Act: 2.0073. Min Act: -0.0000

Data Index: 790327 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.8113. Min Act: -0.0000

Data Index: 221745 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.8382. Min Act: -0.0001

Data Index: 573963 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.9326. Min Act: -0.0001

Data Index: 281409 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.8289. Min Act: -0.0001

Data Index: 1205253 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.8124. Min Act: -0.0000

Data Index: 1076651 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.7947. Min Act: -0.0000

Data Index: 225373 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.8023. Min Act: -0.0001

Data Index: 364712 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.6706. Min Act: -0.0000

Data Index: 833855 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.7743. Min Act: -0.0000

Data Index: 583873 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.7292. Min Act: -0.0000

Data Index: 87491 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.6462. Min Act: -0.0001

Data Index: 219558 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.8312. Min Act: -0.0001

Data Index: 916685 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.7288. Min Act: -0.0001

Data Index: 1065219 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.6084. Min Act: -0.0001

Data Index: 944662 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.6081. Min Act: -0.0001

Data Index: 616725 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.7820. Min Act: -0.0000

Data Index: 729130 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 2.2297. Min Range: -2.2297

Max Act: 1.6841. Min Act: -0.0001

Data Index: 553065 (C4 (Web Text))

Max Activating Token Index: 278