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

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

Neuron 4515 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2386. Min Act: -0.0000

Data Index: 804671 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1583611 (Python Code)

Max Activating Token Index: 989

Text #2

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1372415 (Python Code)

Max Activating Token Index: 681

Text #3

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2167. Min Act: -0.0000

Data Index: 502446 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2233. Min Act: -0.0000

Data Index: 875255 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1468283 (Python Code)

Max Activating Token Index: 916

Text #6

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2147. Min Act: -0.0000

Data Index: 173597 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2200. Min Act: -0.0000

Data Index: 825048 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2167. Min Act: -0.0000

Data Index: 565902 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1996. Min Act: -0.0000

Data Index: 732234 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1145866 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.2122. Min Act: -0.0000

Data Index: 729612 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1963. Min Act: -0.0000

Data Index: 778568 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1987. Min Act: -0.0000

Data Index: 879083 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1956. Min Act: -0.0000

Data Index: 893728 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1947. Min Act: -0.0000

Data Index: 351271 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1566424 (Python Code)

Max Activating Token Index: 918

Text #17

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1957. Min Act: -0.0000

Data Index: 576747 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1987. Min Act: -0.0000

Data Index: 451428 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.2897. Min Range: -0.2897

Max Act: 0.1991. Min Act: -0.0000

Data Index: 787451 (C4 (Web Text))

Max Activating Token Index: 184