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

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

Neuron 58 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: 2.2890. Min Range: -2.2890

Max Act: 2.2890. Min Act: -0.0000

Data Index: 1091167 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9724. Min Act: -0.0000

Data Index: 1261090 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9641. Min Act: -0.0000

Data Index: 660046 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0538. Min Act: -0.0000

Data Index: 727088 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 2.2890. Min Range: -2.2890

Max Act: 2.0216. Min Act: -0.0000

Data Index: 1276463 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9321. Min Act: -0.0000

Data Index: 108862 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.9115. Min Act: -0.0000

Data Index: 121810 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.8462. Min Act: -0.0000

Data Index: 644904 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.8075. Min Act: -0.0000

Data Index: 542039 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.7909. Min Act: -0.0000

Data Index: 914502 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.7667. Min Act: -0.0000

Data Index: 1240658 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.8046. Min Act: -0.0000

Data Index: 216564 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.6683. Min Act: -0.0000

Data Index: 1169029 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.7672. Min Act: -0.0000

Data Index: 1519440 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.6473. Min Act: -0.0000

Data Index: 83877 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.5797. Min Act: -0.0000

Data Index: 1236144 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.6445. Min Act: -0.0000

Data Index: 423149 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1330064 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.7129. Min Act: -0.0000

Data Index: 747072 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 2.2890. Min Range: -2.2890

Max Act: 1.5504. Min Act: -0.0000

Data Index: 1286725 (C4 (Web Text))

Max Activating Token Index: 739