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

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

Neuron 5487 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.9018. Min Act: -0.0000

Data Index: 865762 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.3735. Min Act: -0.0000

Data Index: 659760 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.4489. Min Act: -0.0000

Data Index: 861058 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.4506. Min Act: -0.0000

Data Index: 255440 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.4378. Min Act: -0.0000

Data Index: 772801 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.2744. Min Act: -0.0000

Data Index: 627229 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.2775. Min Act: -0.0000

Data Index: 30329 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.2710. Min Act: -0.0000

Data Index: 812613 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.3305. Min Act: -0.0000

Data Index: 177520 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.3223. Min Act: -0.0000

Data Index: 71730 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.2742. Min Act: -0.0000

Data Index: 453438 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.3577. Min Act: -0.0000

Data Index: 875069 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1153489 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.3313. Min Act: -0.0000

Data Index: 1103587 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.2836. Min Act: -0.0000

Data Index: 816413 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.2995. Min Act: -0.0000

Data Index: 1287909 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.2934. Min Act: -0.0000

Data Index: 189324 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.2932. Min Act: -0.0000

Data Index: 405327 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.2877. Min Act: -0.0000

Data Index: 339941 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.3306. Min Act: -0.0000

Data Index: 798074 (C4 (Web Text))

Max Activating Token Index: 264