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

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

Neuron 1112 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1639119 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1544952 (Python Code)

Max Activating Token Index: 305

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1504358 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1545160 (Python Code)

Max Activating Token Index: 950

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1546499 (Python Code)

Max Activating Token Index: 862

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1412364 (Python Code)

Max Activating Token Index: 709

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1482515 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0129. Min Act: -0.0003

Data Index: 441116 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0127. Min Act: -0.0003

Data Index: 581650 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0127. Min Act: -0.0003

Data Index: 134780 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0124. Min Act: -0.0003

Data Index: 601107 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0124. Min Act: -0.0003

Data Index: 201055 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1589835 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1380656 (Python Code)

Max Activating Token Index: 416

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1458316 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0119. Min Act: -0.0004

Data Index: 160424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1590580 (Python Code)

Max Activating Token Index: 241

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0120. Min Act: -0.0004

Data Index: 364752 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1466265 (Python Code)

Max Activating Token Index: 570

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1461763 (Python Code)

Max Activating Token Index: 870