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

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

Neuron 5944 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.7409. Min Act: -0.0000

Data Index: 1307647 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.7614. Min Act: -0.0001

Data Index: 535548 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.5305. Min Act: -0.0000

Data Index: 91259 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.6150. Min Act: -0.0000

Data Index: 1147551 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.4358. Min Act: -0.0000

Data Index: 170730 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.3827. Min Act: -0.0000

Data Index: 1054929 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.4553. Min Act: -0.0000

Data Index: 973046 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.3680. Min Act: -0.0000

Data Index: 575914 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.2554. Min Act: -0.0001

Data Index: 817986 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.2009. Min Act: -0.0000

Data Index: 207226 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.0747. Min Act: -0.0000

Data Index: 921393 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.1704. Min Act: -0.0000

Data Index: 1002450 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.2862. Min Act: -0.0001

Data Index: 858388 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.2512. Min Act: -0.0001

Data Index: 418051 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.0074. Min Act: -0.0000

Data Index: 1299609 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.2394. Min Act: -0.0000

Data Index: 1219484 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.1015. Min Act: -0.0000

Data Index: 1078811 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.0866. Min Act: -0.0000

Data Index: 1270922 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.1675. Min Act: -0.0000

Data Index: 752988 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 2.7614. Min Range: -2.7614

Max Act: 2.0341. Min Act: -0.0000

Data Index: 585690 (C4 (Web Text))

Max Activating Token Index: 674