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

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

Neuron 2025 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4961. Min Range: -4.4961

Max Act: 4.4961. Min Act: -0.0000

Data Index: 917179 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 4.4961. Min Range: -4.4961

Max Act: 3.7615. Min Act: -0.0000

Data Index: 418588 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 4.4961. Min Range: -4.4961

Max Act: 3.8381. Min Act: -0.0000

Data Index: 343659 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 4.4961. Min Range: -4.4961

Max Act: 3.7679. Min Act: -0.0000

Data Index: 1088758 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 4.4961. Min Range: -4.4961

Max Act: 3.3460. Min Act: -0.0000

Data Index: 685515 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 4.4961. Min Range: -4.4961

Max Act: 3.2036. Min Act: -0.0000

Data Index: 893667 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 4.4961. Min Range: -4.4961

Max Act: 3.2739. Min Act: -0.0000

Data Index: 672103 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 4.4961. Min Range: -4.4961

Max Act: 3.0676. Min Act: -0.0000

Data Index: 513237 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 4.4961. Min Range: -4.4961

Max Act: 3.2060. Min Act: -0.0000

Data Index: 1036161 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.6920. Min Act: -0.0000

Data Index: 872431 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.8431. Min Act: -0.0000

Data Index: 185148 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.8406. Min Act: -0.0000

Data Index: 70092 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.6604. Min Act: -0.0000

Data Index: 361743 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.7413. Min Act: -0.0000

Data Index: 985981 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.8784. Min Act: -0.0000

Data Index: 667823 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.7386. Min Act: -0.0000

Data Index: 148541 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.7328. Min Act: -0.0000

Data Index: 303177 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.7094. Min Act: -0.0000

Data Index: 913411 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.8151. Min Act: -0.0000

Data Index: 1204027 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 4.4961. Min Range: -4.4961

Max Act: 2.8162. Min Act: -0.0000

Data Index: 108995 (C4 (Web Text))

Max Activating Token Index: 512