Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 6 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0005

Data Index: 1613708 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1538389 (Python Code)

Max Activating Token Index: 712

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1395146 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1623418 (Python Code)

Max Activating Token Index: 645

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1462153 (Python Code)

Max Activating Token Index: 565

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0149. Min Act: -0.0005

Data Index: 1588921 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0149. Min Act: -0.0005

Data Index: 621752 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1416127 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0143. Min Act: -0.0006

Data Index: 407634 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1516150 (Python Code)

Max Activating Token Index: 805

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1364904 (Python Code)

Max Activating Token Index: 676

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1418299 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1579424 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1363651 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1526342 (Python Code)

Max Activating Token Index: 311

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1427222 (Python Code)

Max Activating Token Index: 634

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1490568 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1438340 (Python Code)

Max Activating Token Index: 806

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1646216 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0141. Min Act: -0.0005

Data Index: 1519524 (Python Code)

Max Activating Token Index: 789