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

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

Neuron 485 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1946. Min Range: -3.1946

Max Act: 3.1946. Min Act: -0.0001

Data Index: 1093560 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8069. Min Act: -0.0001

Data Index: 1105785 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.7545. Min Act: -0.0001

Data Index: 1230283 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.6003. Min Act: -0.0001

Data Index: 912701 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.6631. Min Act: -0.0001

Data Index: 165277 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.5890. Min Act: -0.0001

Data Index: 322922 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.5154. Min Act: -0.0001

Data Index: 150481 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.5698. Min Act: -0.0001

Data Index: 418712 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.5598. Min Act: -0.0001

Data Index: 1302633 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.3601. Min Act: -0.0001

Data Index: 731303 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.6147. Min Act: -0.0001

Data Index: 561821 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.6021. Min Act: -0.0001

Data Index: 387048 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.5312. Min Act: -0.0001

Data Index: 1322878 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.4599. Min Act: -0.0001

Data Index: 971850 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.5846. Min Act: -0.0001

Data Index: 595583 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.4950. Min Act: -0.0001

Data Index: 1245637 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.6268. Min Act: -0.0001

Data Index: 371917 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.3662. Min Act: -0.0001

Data Index: 45601 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.5529. Min Act: -0.0001

Data Index: 991552 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.5179. Min Act: -0.0001

Data Index: 1092653 (C4 (Web Text))

Max Activating Token Index: 22