Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1943 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.6004. Min Act: -0.0001

Data Index: 151801 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.6208. Min Act: -0.0001

Data Index: 423543 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5222. Min Act: -0.0001

Data Index: 849871 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5997. Min Act: -0.0001

Data Index: 1536585 (Python Code)

Max Activating Token Index: 1006

Text #4

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5719. Min Act: -0.0001

Data Index: 771791 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5832. Min Act: -0.0001

Data Index: 1641509 (Python Code)

Max Activating Token Index: 939

Text #6

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5131. Min Act: -0.0001

Data Index: 137369 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4866. Min Act: -0.0001

Data Index: 1121111 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5763. Min Act: -0.0001

Data Index: 327840 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4681. Min Act: -0.0001

Data Index: 1525961 (Python Code)

Max Activating Token Index: 877

Text #10

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4835. Min Act: -0.0001

Data Index: 969209 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.5187. Min Act: -0.0001

Data Index: 614211 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4631. Min Act: -0.0001

Data Index: 826794 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4801. Min Act: -0.0001

Data Index: 9065 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4261. Min Act: -0.0001

Data Index: 124191 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4824. Min Act: -0.0001

Data Index: 635299 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4711. Min Act: -0.0001

Data Index: 887822 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4420. Min Act: -0.0001

Data Index: 295858 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4504. Min Act: -0.0001

Data Index: 869442 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.6208. Min Range: -0.6208

Max Act: 0.4503. Min Act: -0.0001

Data Index: 5259 (C4 (Web Text))

Max Activating Token Index: 551