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

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

Neuron 1218 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1054349 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1080920 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1121735 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1294975 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6821. Min Act: -0.0000

Data Index: 304253 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6404. Min Act: -0.0000

Data Index: 223930 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1062156 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6440. Min Act: -0.0000

Data Index: 971737 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6416. Min Act: -0.0000

Data Index: 26443 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6215. Min Act: -0.0000

Data Index: 491153 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6406. Min Act: -0.0000

Data Index: 76578 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6539. Min Act: -0.0000

Data Index: 717177 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1010776 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1225991 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1122563 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6426. Min Act: -0.0000

Data Index: 581650 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6291. Min Act: -0.0000

Data Index: 447166 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6536. Min Act: -0.0000

Data Index: 994383 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1285002 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5922. Min Act: -0.0000

Data Index: 1039438 (C4 (Web Text))

Max Activating Token Index: 104