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

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

Neuron 4036 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: 1.4817. Min Range: -1.4817

Max Act: 1.4817. Min Act: -0.0000

Data Index: 1354907 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3047. Min Act: -0.0000

Data Index: 1232564 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2990. Min Act: -0.0000

Data Index: 281793 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2152. Min Act: -0.0000

Data Index: 604266 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2480. Min Act: -0.0000

Data Index: 278215 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.2424. Min Act: -0.0000

Data Index: 624949 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1677. Min Act: -0.0000

Data Index: 463174 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1654. Min Act: -0.0000

Data Index: 596859 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1689. Min Act: -0.0000

Data Index: 292092 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1092. Min Act: -0.0000

Data Index: 466290 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0806. Min Act: -0.0000

Data Index: 581094 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1177. Min Act: -0.0000

Data Index: 221964 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0966. Min Act: -0.0000

Data Index: 1000182 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1063769 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1048277 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1300. Min Act: -0.0000

Data Index: 128562 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0544. Min Act: -0.0000

Data Index: 779445 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1100190 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0363. Min Act: -0.0000

Data Index: 206394 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.9955. Min Act: -0.0000

Data Index: 974968 (C4 (Web Text))

Max Activating Token Index: 517