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

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

Neuron 3434 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: 0.6515. Min Range: -0.6515

Max Act: 0.6515. Min Act: -0.0000

Data Index: 240186 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1217376 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1136543 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4795. Min Act: -0.0000

Data Index: 161295 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4847. Min Act: -0.0000

Data Index: 371977 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4324. Min Act: -0.0000

Data Index: 502548 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4446. Min Act: -0.0000

Data Index: 473939 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.3768. Min Act: -0.0000

Data Index: 412381 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4228. Min Act: -0.0000

Data Index: 313799 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4094. Min Act: -0.0000

Data Index: 920223 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4172. Min Act: -0.0000

Data Index: 850401 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4477. Min Act: -0.0000

Data Index: 672696 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1170984 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.3898. Min Act: -0.0000

Data Index: 757848 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4036. Min Act: -0.0000

Data Index: 628379 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1329805 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4260. Min Act: -0.0000

Data Index: 435745 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.4106. Min Act: -0.0000

Data Index: 496743 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.3964. Min Act: -0.0000

Data Index: 49469 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.6515. Min Range: -0.6515

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1070628 (C4 (Web Text))

Max Activating Token Index: 660