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

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

Neuron 4951 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1295993 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1199053 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5147. Min Act: -0.0000

Data Index: 441897 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5107. Min Act: -0.0000

Data Index: 979786 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.5037. Min Act: -0.0000

Data Index: 545514 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4624. Min Act: -0.0000

Data Index: 662815 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1020387 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1148555 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4354. Min Act: -0.0000

Data Index: 729816 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1031748 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1319583 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4796. Min Act: -0.0000

Data Index: 863539 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4463. Min Act: -0.0000

Data Index: 42110 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4501. Min Act: -0.0000

Data Index: 693697 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1317464 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4782. Min Act: -0.0000

Data Index: 395852 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4163. Min Act: -0.0000

Data Index: 567290 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4490. Min Act: -0.0000

Data Index: 999452 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4523. Min Act: -0.0000

Data Index: 67941 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.5602. Min Range: -0.5602

Max Act: 0.4280. Min Act: -0.0000

Data Index: 340148 (C4 (Web Text))

Max Activating Token Index: 568