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

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

Neuron 3693 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: 9.0813. Min Range: -9.0813

Max Act: 9.0813. Min Act: -0.0000

Data Index: 1060416 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 9.0813. Min Range: -9.0813

Max Act: 8.0319. Min Act: -0.0000

Data Index: 195766 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 9.0813. Min Range: -9.0813

Max Act: 7.9524. Min Act: -0.0000

Data Index: 13388 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 9.0813. Min Range: -9.0813

Max Act: 7.7761. Min Act: -0.0000

Data Index: 716804 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 9.0813. Min Range: -9.0813

Max Act: 6.3232. Min Act: -0.0001

Data Index: 931806 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 9.0813. Min Range: -9.0813

Max Act: 6.0066. Min Act: -0.0001

Data Index: 301047 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.4978. Min Act: -0.0001

Data Index: 447600 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.4430. Min Act: -0.0000

Data Index: 555771 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.5982. Min Act: -0.0001

Data Index: 704952 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.5327. Min Act: -0.0000

Data Index: 493381 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.1797. Min Act: -0.0001

Data Index: 633377 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.1463. Min Act: -0.0000

Data Index: 177226 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.1209. Min Act: -0.0000

Data Index: 617687 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 9.0813. Min Range: -9.0813

Max Act: 2.9568. Min Act: -0.0000

Data Index: 680640 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.2849. Min Act: -0.0000

Data Index: 329959 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.2821. Min Act: -0.0001

Data Index: 926274 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.2818. Min Act: -0.0000

Data Index: 915873 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 9.0813. Min Range: -9.0813

Max Act: 2.9829. Min Act: -0.0000

Data Index: 984739 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 9.0813. Min Range: -9.0813

Max Act: 2.9830. Min Act: -0.0000

Data Index: 1098349 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 9.0813. Min Range: -9.0813

Max Act: 3.2472. Min Act: -0.0000

Data Index: 1336402 (C4 (Web Text))

Max Activating Token Index: 1015