Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3772 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.3853. Min Act: -0.0001

Data Index: 485527 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.3956. Min Act: -0.0000

Data Index: 7614 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.3759. Min Act: -0.0000

Data Index: 478036 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1048929 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2699. Min Act: -0.0001

Data Index: 896123 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1299105 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2567. Min Act: -0.0001

Data Index: 253185 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2924. Min Act: -0.0000

Data Index: 165472 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1019693 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2463. Min Act: -0.0000

Data Index: 695379 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2561. Min Act: -0.0001

Data Index: 502381 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2417. Min Act: -0.0000

Data Index: 389181 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2600. Min Act: -0.0000

Data Index: 584008 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1211851 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2293. Min Act: -0.0000

Data Index: 147234 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2392. Min Act: -0.0000

Data Index: 743941 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2089. Min Act: -0.0000

Data Index: 736758 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.1942. Min Act: -0.0001

Data Index: 816120 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1278898 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.3956. Min Range: -0.3956

Max Act: 0.2248. Min Act: -0.0000

Data Index: 925463 (C4 (Web Text))

Max Activating Token Index: 748