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

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

Neuron 1547 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0264. Min Range: -2.0264

Max Act: 2.0264. Min Act: -0.0000

Data Index: 294859 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.8264. Min Act: -0.0000

Data Index: 616262 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.6256. Min Act: -0.0000

Data Index: 185654 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.4884. Min Act: -0.0000

Data Index: 497019 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.4781. Min Act: -0.0001

Data Index: 1172030 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.3715. Min Act: -0.0000

Data Index: 534842 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.3395. Min Act: -0.0001

Data Index: 438495 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.2572. Min Act: -0.0000

Data Index: 751749 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.2816. Min Act: -0.0000

Data Index: 512158 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.2780. Min Act: -0.0000

Data Index: 32674 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.1997. Min Act: -0.0001

Data Index: 910503 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.2165. Min Act: -0.0001

Data Index: 186735 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.1882. Min Act: -0.0001

Data Index: 959330 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.2079. Min Act: -0.0001

Data Index: 614983 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.1273. Min Act: -0.0001

Data Index: 433891 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.0768. Min Act: -0.0000

Data Index: 801298 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.1060. Min Act: -0.0000

Data Index: 553243 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.0395. Min Act: -0.0000

Data Index: 182355 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.1301. Min Act: -0.0001

Data Index: 837612 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 2.0264. Min Range: -2.0264

Max Act: 1.0936. Min Act: -0.0000

Data Index: 219882 (C4 (Web Text))

Max Activating Token Index: 259