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

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

Neuron 380 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: 1.8144. Min Range: -1.8144

Max Act: 1.8144. Min Act: -0.0001

Data Index: 1104494 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.6220. Min Act: -0.0001

Data Index: 853954 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.4087. Min Act: -0.0001

Data Index: 459506 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.5594. Min Act: -0.0001

Data Index: 423052 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.3900. Min Act: -0.0001

Data Index: 85667 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.3163. Min Act: -0.0001

Data Index: 629560 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.3224. Min Act: -0.0001

Data Index: 731102 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.3032. Min Act: -0.0001

Data Index: 24899 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.2812. Min Act: -0.0001

Data Index: 802529 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.2374. Min Act: -0.0001

Data Index: 414158 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.2897. Min Act: -0.0001

Data Index: 1066472 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.3304. Min Act: -0.0001

Data Index: 979036 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.4945. Min Act: -0.0001

Data Index: 629538 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.3101. Min Act: -0.0001

Data Index: 537245 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.3482. Min Act: -0.0001

Data Index: 1113671 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.3067. Min Act: -0.0001

Data Index: 975109 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.4231. Min Act: -0.0001

Data Index: 1283906 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.3314. Min Act: -0.0001

Data Index: 181266 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.2879. Min Act: -0.0001

Data Index: 893743 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 1.8144. Min Range: -1.8144

Max Act: 1.2011. Min Act: -0.0001

Data Index: 21620 (C4 (Web Text))

Max Activating Token Index: 561