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

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

Neuron 2137 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8707. Min Act: -0.0001

Data Index: 962326 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.8688. Min Act: -0.0001

Data Index: 949853 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.7879. Min Act: -0.0001

Data Index: 979689 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5983. Min Act: -0.0001

Data Index: 652739 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.7039. Min Act: -0.0001

Data Index: 486338 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6651. Min Act: -0.0001

Data Index: 590823 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5940. Min Act: -0.0001

Data Index: 718503 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5905. Min Act: -0.0001

Data Index: 1339992 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6004. Min Act: -0.0001

Data Index: 1383449 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5831. Min Act: -0.0001

Data Index: 432537 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5783. Min Act: -0.0001

Data Index: 993658 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5312. Min Act: -0.0001

Data Index: 51999 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.6310. Min Act: -0.0001

Data Index: 824732 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5426. Min Act: -0.0001

Data Index: 620398 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5315. Min Act: -0.0001

Data Index: 500382 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5633. Min Act: -0.0001

Data Index: 209438 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5197. Min Act: -0.0001

Data Index: 771602 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5494. Min Act: -0.0001

Data Index: 29525 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.4963. Min Act: -0.0001

Data Index: 821052 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.8707. Min Range: -0.8707

Max Act: 0.5255. Min Act: -0.0001

Data Index: 999293 (C4 (Web Text))

Max Activating Token Index: 784