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

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

Neuron 4892 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.8365. Min Act: -0.0001

Data Index: 1145009 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7145. Min Act: -0.0001

Data Index: 237194 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.8026. Min Act: -0.0001

Data Index: 394650 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1284783 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7308. Min Act: -0.0001

Data Index: 1148372 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7930. Min Act: -0.0001

Data Index: 783366 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7050. Min Act: -0.0001

Data Index: 145910 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7498. Min Act: -0.0001

Data Index: 393545 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7350. Min Act: -0.0001

Data Index: 613809 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7201. Min Act: -0.0001

Data Index: 779900 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.6563. Min Act: -0.0001

Data Index: 126186 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7304. Min Act: -0.0001

Data Index: 1126858 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7043. Min Act: -0.0001

Data Index: 1315309 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.8081. Min Act: -0.0001

Data Index: 55780 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.7154. Min Act: -0.0001

Data Index: 956408 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.6399. Min Act: -0.0001

Data Index: 1085501 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.5942. Min Act: -0.0001

Data Index: 474498 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.6585. Min Act: -0.0001

Data Index: 414157 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.6214. Min Act: -0.0001

Data Index: 50770 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.8365. Min Range: -0.8365

Max Act: 0.6992. Min Act: -0.0001

Data Index: 460864 (C4 (Web Text))

Max Activating Token Index: 299