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

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

Neuron 689 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3943. Min Act: -0.0001

Data Index: 1429161 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2925. Min Act: -0.0001

Data Index: 854369 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3014. Min Act: -0.0001

Data Index: 1389109 (Python Code)

Max Activating Token Index: 159

Text #3

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.3223. Min Act: -0.0001

Data Index: 1546345 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2917. Min Act: -0.0001

Data Index: 1378143 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2083. Min Act: -0.0001

Data Index: 1477657 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1961. Min Act: -0.0001

Data Index: 1467362 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1844. Min Act: -0.0001

Data Index: 1506079 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.0778. Min Act: -0.0001

Data Index: 748638 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1347. Min Act: -0.0001

Data Index: 1529125 (Python Code)

Max Activating Token Index: 219

Text #10

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1233. Min Act: -0.0001

Data Index: 1455229 (Python Code)

Max Activating Token Index: 893

Text #11

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.0089. Min Act: -0.0001

Data Index: 441518 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2173. Min Act: -0.0001

Data Index: 1024522 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1037. Min Act: -0.0001

Data Index: 315194 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.0028. Min Act: -0.0001

Data Index: 1321295 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.0793. Min Act: -0.0001

Data Index: 1509784 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1111. Min Act: -0.0001

Data Index: 1611043 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.0504. Min Act: -0.0001

Data Index: 1372335 (Python Code)

Max Activating Token Index: 926

Text #18

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.0798. Min Act: -0.0001

Data Index: 1562724 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.1130. Min Act: -0.0001

Data Index: 1501793 (Python Code)

Max Activating Token Index: 250