Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 234 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.0276. Min Range: -5.0276

Max Act: 5.0276. Min Act: -0.0001

Data Index: 1033052 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.9964. Min Act: -0.0000

Data Index: 1276882 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.8181. Min Act: -0.0001

Data Index: 652451 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.5793. Min Act: -0.0001

Data Index: 509483 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.6606. Min Act: -0.0001

Data Index: 650846 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.4077. Min Act: -0.0001

Data Index: 1265940 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.2936. Min Act: -0.0001

Data Index: 435290 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.0969. Min Act: -0.0000

Data Index: 1271725 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.2203. Min Act: -0.0001

Data Index: 1264333 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.1414. Min Act: -0.0001

Data Index: 683481 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.0248. Min Act: -0.0001

Data Index: 1271809 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 5.0276. Min Range: -5.0276

Max Act: 3.9896. Min Act: -0.0001

Data Index: 1121897 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 5.0276. Min Range: -5.0276

Max Act: 4.1241. Min Act: -0.0001

Data Index: 1239505 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 5.0276. Min Range: -5.0276

Max Act: 3.7710. Min Act: -0.0000

Data Index: 259433 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 5.0276. Min Range: -5.0276

Max Act: 3.6165. Min Act: -0.0001

Data Index: 3202 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 5.0276. Min Range: -5.0276

Max Act: 3.7682. Min Act: -0.0000

Data Index: 576488 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 5.0276. Min Range: -5.0276

Max Act: 3.5248. Min Act: -0.0000

Data Index: 693668 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 5.0276. Min Range: -5.0276

Max Act: 3.3555. Min Act: -0.0001

Data Index: 904788 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 5.0276. Min Range: -5.0276

Max Act: 3.4597. Min Act: -0.0001

Data Index: 1081917 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 5.0276. Min Range: -5.0276

Max Act: 3.4116. Min Act: -0.0001

Data Index: 108415 (C4 (Web Text))

Max Activating Token Index: 936