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

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

Neuron 4913 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.6437. Min Act: -0.0000

Data Index: 298235 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1296713 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4508. Min Act: -0.0000

Data Index: 134916 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1045353 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4591. Min Act: -0.0000

Data Index: 909521 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4338. Min Act: -0.0000

Data Index: 998400 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4256. Min Act: -0.0000

Data Index: 927550 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4195. Min Act: 0.0000

Data Index: 1031868 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4043. Min Act: -0.0000

Data Index: 788916 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4017. Min Act: -0.0000

Data Index: 446952 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4156. Min Act: 0.0000

Data Index: 861381 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.3964. Min Act: -0.0000

Data Index: 469272 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.3806. Min Act: -0.0000

Data Index: 999406 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4036. Min Act: -0.0000

Data Index: 694912 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1301987 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1067532 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.3862. Min Act: -0.0000

Data Index: 917835 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.3865. Min Act: -0.0000

Data Index: 692736 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1268612 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.6437. Min Range: -0.6437

Max Act: 0.3830. Min Act: -0.0000

Data Index: 120244 (C4 (Web Text))

Max Activating Token Index: 16