Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1306 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0006

Data Index: 733422 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1487881 (Python Code)

Max Activating Token Index: 378

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0136. Min Act: -0.0006

Data Index: 158445 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1075723 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0135. Min Act: -0.0006

Data Index: 801214 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1536118 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1540926 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0124. Min Act: -0.0005

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1631637 (Python Code)

Max Activating Token Index: 407

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1519919 (Python Code)

Max Activating Token Index: 706

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0006

Data Index: 150235 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0126. Min Act: -0.0005

Data Index: 357583 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1012932 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1464384 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0006

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1408364 (Python Code)

Max Activating Token Index: 185

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0006

Data Index: 537534 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0119. Min Act: -0.0006

Data Index: 956756 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0116. Min Act: -0.0006

Data Index: 702363 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1410014 (Python Code)

Max Activating Token Index: 422