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

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

Neuron 2360 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4405. Min Range: -2.4405

Max Act: 2.3967. Min Act: -0.0000

Data Index: 566532 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 2.4405. Min Range: -2.4405

Max Act: 2.4405. Min Act: -0.0000

Data Index: 569246 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.8984. Min Act: -0.0000

Data Index: 692764 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.8214. Min Act: -0.0000

Data Index: 464896 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.7509. Min Act: -0.0000

Data Index: 990064 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.6222. Min Act: -0.0000

Data Index: 632840 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.6358. Min Act: -0.0000

Data Index: 1178153 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.6286. Min Act: -0.0000

Data Index: 516175 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.4468. Min Act: -0.0000

Data Index: 10132 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.5202. Min Act: -0.0000

Data Index: 1017215 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.4240. Min Act: -0.0000

Data Index: 703242 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.5128. Min Act: -0.0000

Data Index: 674882 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.5038. Min Act: -0.0000

Data Index: 1056038 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.4768. Min Act: -0.0000

Data Index: 206886 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.4682. Min Act: -0.0000

Data Index: 576874 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.4596. Min Act: -0.0000

Data Index: 524562 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.4355. Min Act: -0.0000

Data Index: 501392 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.2763. Min Act: -0.0000

Data Index: 238779 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.5188. Min Act: -0.0000

Data Index: 1112359 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 2.4405. Min Range: -2.4405

Max Act: 1.4231. Min Act: -0.0000

Data Index: 27408 (C4 (Web Text))

Max Activating Token Index: 865