Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 4 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.2051. Min Act: -0.0001

Data Index: 801506 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1996. Min Act: -0.0001

Data Index: 6290 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.2055. Min Act: -0.0001

Data Index: 972432 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1934. Min Act: -0.0001

Data Index: 664556 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1996. Min Act: -0.0001

Data Index: 214822 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1901. Min Act: -0.0001

Data Index: 590239 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1125683 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1942. Min Act: -0.0001

Data Index: 36363 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1329627 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1006040 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1963. Min Act: -0.0001

Data Index: 353257 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1109154 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1886. Min Act: -0.0001

Data Index: 848401 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1941. Min Act: -0.0001

Data Index: 1186572 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1881. Min Act: -0.0001

Data Index: 710923 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1814. Min Act: -0.0001

Data Index: 941150 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1938. Min Act: -0.0001

Data Index: 418692 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1821. Min Act: -0.0001

Data Index: 670697 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1817. Min Act: -0.0001

Data Index: 1159334 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.2055. Min Range: -0.2055

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1191302 (C4 (Web Text))

Max Activating Token Index: 922