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

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

Neuron 3420 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.8601. Min Act: -0.0000

Data Index: 773647 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.8327. Min Act: -0.0000

Data Index: 156380 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7855. Min Act: -0.0000

Data Index: 271392 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7992. Min Act: 0.0000

Data Index: 87628 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7976. Min Act: -0.0000

Data Index: 697242 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7342. Min Act: -0.0000

Data Index: 614276 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7439. Min Act: 0.0000

Data Index: 642390 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7541. Min Act: -0.0000

Data Index: 574443 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7492. Min Act: -0.0000

Data Index: 160682 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1260399 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1293120 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7082. Min Act: -0.0000

Data Index: 151258 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6766. Min Act: 0.0001

Data Index: 1053520 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1004093 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.7131. Min Act: 0.0000

Data Index: 669014 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6881. Min Act: 0.0000

Data Index: 1301725 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1183822 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6655. Min Act: -0.0000

Data Index: 261666 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1307899 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.8601. Min Range: -0.8601

Max Act: 0.6845. Min Act: -0.0000

Data Index: 67791 (C4 (Web Text))

Max Activating Token Index: 503