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

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

Neuron 5461 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.4849. Min Act: -0.0000

Data Index: 698619 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.4459. Min Act: -0.0000

Data Index: 1199356 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.2374. Min Act: -0.0000

Data Index: 947640 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 3.4849. Min Range: -3.4849

Max Act: 3.1841. Min Act: -0.0000

Data Index: 821671 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.8552. Min Act: -0.0000

Data Index: 586314 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.7528. Min Act: -0.0000

Data Index: 703813 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.5667. Min Act: -0.0000

Data Index: 1227739 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.5055. Min Act: -0.0000

Data Index: 409064 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.4624. Min Act: -0.0000

Data Index: 72083 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.6408. Min Act: -0.0000

Data Index: 479636 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.3422. Min Act: -0.0000

Data Index: 1191496 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.1058. Min Act: -0.0000

Data Index: 298710 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.3405. Min Act: -0.0000

Data Index: 159904 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.2587. Min Act: -0.0000

Data Index: 561240 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.1077. Min Act: -0.0000

Data Index: 1125860 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.0358. Min Act: -0.0000

Data Index: 670559 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 3.4849. Min Range: -3.4849

Max Act: 2.2529. Min Act: -0.0000

Data Index: 931799 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 3.4849. Min Range: -3.4849

Max Act: 1.9340. Min Act: -0.0000

Data Index: 195956 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 3.4849. Min Range: -3.4849

Max Act: 1.7829. Min Act: -0.0000

Data Index: 543320 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 3.4849. Min Range: -3.4849

Max Act: 1.8824. Min Act: -0.0000

Data Index: 46821 (C4 (Web Text))

Max Activating Token Index: 977