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

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

Neuron 1095 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: 2.4964. Min Range: -2.4964

Max Act: 2.4964. Min Act: -0.0000

Data Index: 189021 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 2.4964. Min Range: -2.4964

Max Act: 2.2058. Min Act: -0.0000

Data Index: 1651591 (Python Code)

Max Activating Token Index: 752

Text #2

Max Range: 2.4964. Min Range: -2.4964

Max Act: 2.0042. Min Act: -0.0000

Data Index: 21529 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 2.4964. Min Range: -2.4964

Max Act: 2.0796. Min Act: -0.0000

Data Index: 1449015 (Python Code)

Max Activating Token Index: 439

Text #4

Max Range: 2.4964. Min Range: -2.4964

Max Act: 2.0685. Min Act: -0.0000

Data Index: 239290 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.9454. Min Act: -0.0000

Data Index: 1488963 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.9133. Min Act: -0.0000

Data Index: 349001 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.8796. Min Act: -0.0000

Data Index: 155919 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.8423. Min Act: -0.0000

Data Index: 1550961 (Python Code)

Max Activating Token Index: 635

Text #9

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.9243. Min Act: -0.0000

Data Index: 977436 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.9151. Min Act: -0.0000

Data Index: 931031 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.9894. Min Act: -0.0000

Data Index: 1220948 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.8457. Min Act: -0.0000

Data Index: 766955 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.7376. Min Act: -0.0000

Data Index: 945117 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.8201. Min Act: -0.0000

Data Index: 1055521 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.7996. Min Act: -0.0000

Data Index: 1453918 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.8067. Min Act: -0.0000

Data Index: 504181 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.6842. Min Act: -0.0000

Data Index: 586379 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1473109 (Python Code)

Max Activating Token Index: 334

Text #19

Max Range: 2.4964. Min Range: -2.4964

Max Act: 1.7700. Min Act: -0.0000

Data Index: 1351788 (C4 (Web Text))

Max Activating Token Index: 506