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

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

Neuron 2962 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: 2.2888. Min Range: -2.2888

Max Act: 2.2888. Min Act: -0.0000

Data Index: 896184 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 2.2888. Min Range: -2.2888

Max Act: 2.1015. Min Act: -0.0000

Data Index: 1355967 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 2.2888. Min Range: -2.2888

Max Act: 2.1158. Min Act: -0.0000

Data Index: 1048124 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 2.2888. Min Range: -2.2888

Max Act: 2.0890. Min Act: -0.0000

Data Index: 1065400 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.9991. Min Act: -0.0000

Data Index: 226167 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.9797. Min Act: -0.0000

Data Index: 666000 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.8486. Min Act: -0.0000

Data Index: 580220 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.8032. Min Act: -0.0000

Data Index: 430165 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.8933. Min Act: -0.0000

Data Index: 646544 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.8927. Min Act: -0.0000

Data Index: 233319 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.8933. Min Act: -0.0000

Data Index: 494202 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.8728. Min Act: -0.0000

Data Index: 750681 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.8413. Min Act: -0.0000

Data Index: 240202 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.8075. Min Act: -0.0000

Data Index: 195453 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.6839. Min Act: -0.0000

Data Index: 322003 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.7980. Min Act: -0.0000

Data Index: 1245119 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.8871. Min Act: -0.0000

Data Index: 1025049 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.7823. Min Act: -0.0000

Data Index: 1328230 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.7757. Min Act: -0.0000

Data Index: 637385 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 2.2888. Min Range: -2.2888

Max Act: 1.7819. Min Act: -0.0000

Data Index: 979381 (C4 (Web Text))

Max Activating Token Index: 394