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

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

Neuron 470 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4684. Min Range: -4.4684

Max Act: 4.4684. Min Act: -0.0000

Data Index: 1247909 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.4970. Min Act: -0.0000

Data Index: 1210503 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.7329. Min Act: -0.0000

Data Index: 1137459 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.6602. Min Act: -0.0000

Data Index: 430012 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.5982. Min Act: -0.0001

Data Index: 1314317 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.2458. Min Act: -0.0000

Data Index: 8872 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.0651. Min Act: -0.0000

Data Index: 589288 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.0769. Min Act: -0.0000

Data Index: 739575 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.2098. Min Act: -0.0000

Data Index: 349271 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.2694. Min Act: -0.0000

Data Index: 343242 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.1454. Min Act: -0.0001

Data Index: 1342902 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.0816. Min Act: -0.0001

Data Index: 669524 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.0384. Min Act: -0.0000

Data Index: 1055649 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.1600. Min Act: -0.0001

Data Index: 512914 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.1559. Min Act: -0.0000

Data Index: 142006 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 4.4684. Min Range: -4.4684

Max Act: 3.1402. Min Act: -0.0001

Data Index: 416113 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 4.4684. Min Range: -4.4684

Max Act: 2.9175. Min Act: -0.0000

Data Index: 1335278 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 4.4684. Min Range: -4.4684

Max Act: 2.7804. Min Act: -0.0000

Data Index: 87765 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 4.4684. Min Range: -4.4684

Max Act: 2.7719. Min Act: -0.0000

Data Index: 477844 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 4.4684. Min Range: -4.4684

Max Act: 2.6512. Min Act: -0.0000

Data Index: 201414 (C4 (Web Text))

Max Activating Token Index: 1023