Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2557 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.7628. Min Act: -0.0001

Data Index: 1262687 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5588. Min Act: -0.0001

Data Index: 1318173 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6244. Min Act: -0.0001

Data Index: 1141238 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5337. Min Act: -0.0001

Data Index: 475354 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.6811. Min Act: -0.0001

Data Index: 947437 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1182469 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4952. Min Act: -0.0001

Data Index: 147917 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5595. Min Act: -0.0001

Data Index: 1103039 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4220. Min Act: -0.0001

Data Index: 74969 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4431. Min Act: -0.0000

Data Index: 786245 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4846. Min Act: -0.0000

Data Index: 727463 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4374. Min Act: -0.0001

Data Index: 641371 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3007. Min Act: -0.0001

Data Index: 1311542 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4409. Min Act: -0.0001

Data Index: 1184961 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.5113. Min Act: -0.0001

Data Index: 853206 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4649. Min Act: -0.0001

Data Index: 1283306 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4475. Min Act: -0.0001

Data Index: 384862 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3826. Min Act: -0.0001

Data Index: 279040 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.3927. Min Act: -0.0001

Data Index: 6497 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.7628. Min Range: -0.7628

Max Act: 0.4717. Min Act: -0.0001

Data Index: 1299326 (C4 (Web Text))

Max Activating Token Index: 534