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

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

Neuron 147 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2326. Min Range: -4.2326

Max Act: 4.2326. Min Act: -0.0000

Data Index: 85971 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 4.2326. Min Range: -4.2326

Max Act: 3.5841. Min Act: -0.0000

Data Index: 301509 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 4.2326. Min Range: -4.2326

Max Act: 3.5871. Min Act: -0.0000

Data Index: 1011818 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.8507. Min Act: -0.0000

Data Index: 20680 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.9874. Min Act: -0.0000

Data Index: 32920 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.9767. Min Act: -0.0000

Data Index: 316519 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.9407. Min Act: 0.0000

Data Index: 441716 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.9099. Min Act: -0.0001

Data Index: 972073 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.8431. Min Act: -0.0000

Data Index: 872181 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.9903. Min Act: -0.0000

Data Index: 37499 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.9179. Min Act: -0.0000

Data Index: 740384 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.7691. Min Act: -0.0001

Data Index: 963048 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.6325. Min Act: -0.0000

Data Index: 427752 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.8918. Min Act: -0.0000

Data Index: 1290160 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.8650. Min Act: -0.0000

Data Index: 303684 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.7024. Min Act: -0.0001

Data Index: 1192941 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.5696. Min Act: -0.0000

Data Index: 1324788 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.6806. Min Act: -0.0001

Data Index: 304194 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.6737. Min Act: -0.0000

Data Index: 852447 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 4.2326. Min Range: -4.2326

Max Act: 2.5660. Min Act: -0.0000

Data Index: 794334 (C4 (Web Text))

Max Activating Token Index: 723