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

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

Neuron 5824 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5827. Min Act: -0.0000

Data Index: 159801 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5492. Min Act: 0.0000

Data Index: 630812 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1255532 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5363. Min Act: -0.0000

Data Index: 110939 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5016. Min Act: -0.0000

Data Index: 503516 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4704. Min Act: -0.0000

Data Index: 606232 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4951. Min Act: -0.0000

Data Index: 992035 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4816. Min Act: -0.0000

Data Index: 325269 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4584. Min Act: -0.0000

Data Index: 970989 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1106196 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4577. Min Act: -0.0000

Data Index: 307795 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1101770 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4594. Min Act: -0.0000

Data Index: 134689 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1122644 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1182219 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1150708 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4268. Min Act: 0.0000

Data Index: 1074581 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1231773 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1209080 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4131. Min Act: -0.0000

Data Index: 460384 (C4 (Web Text))

Max Activating Token Index: 711