Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 764 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.7522. Min Act: -0.0000

Data Index: 241647 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.5069. Min Act: -0.0000

Data Index: 703525 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1061946 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1077433 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.2698. Min Act: -0.0000

Data Index: 725052 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.1801. Min Act: -0.0000

Data Index: 182642 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.1392. Min Act: -0.0000

Data Index: 185727 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1092308 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1344609 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1159008 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.0496. Min Act: -0.0000

Data Index: 904132 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.0101. Min Act: -0.0000

Data Index: 412332 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1167592 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 1.7522. Min Range: -1.7522

Max Act: 1.0072. Min Act: -0.0000

Data Index: 667388 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 1.7522. Min Range: -1.7522

Max Act: 0.8939. Min Act: -0.0000

Data Index: 673187 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 1.7522. Min Range: -1.7522

Max Act: 0.9635. Min Act: -0.0000

Data Index: 288382 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 1.7522. Min Range: -1.7522

Max Act: 0.9802. Min Act: -0.0000

Data Index: 300358 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.7522. Min Range: -1.7522

Max Act: 0.9678. Min Act: -0.0000

Data Index: 82080 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.7522. Min Range: -1.7522

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1117148 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 1.7522. Min Range: -1.7522

Max Act: 0.9955. Min Act: -0.0000

Data Index: 150378 (C4 (Web Text))

Max Activating Token Index: 682