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

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

Neuron 1712 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.4109. Min Act: -0.0001

Data Index: 210889 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3704. Min Act: -0.0001

Data Index: 342490 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1112890 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3101. Min Act: -0.0001

Data Index: 1319290 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3189. Min Act: -0.0001

Data Index: 971173 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3504. Min Act: -0.0001

Data Index: 989791 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3158. Min Act: -0.0001

Data Index: 886592 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3111. Min Act: -0.0001

Data Index: 769023 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3107. Min Act: -0.0001

Data Index: 1207089 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3203. Min Act: -0.0001

Data Index: 362242 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1071099 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3179. Min Act: -0.0001

Data Index: 1347842 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.2900. Min Act: -0.0001

Data Index: 506891 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1256153 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3020. Min Act: -0.0001

Data Index: 47862 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3019. Min Act: -0.0001

Data Index: 1088502 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1264389 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.2848. Min Act: -0.0000

Data Index: 447530 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.2834. Min Act: -0.0001

Data Index: 623559 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.2925. Min Act: -0.0001

Data Index: 582462 (C4 (Web Text))

Max Activating Token Index: 719