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

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

Neuron 1773 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: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1294670 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0168. Min Act: -0.0006

Data Index: 1604963 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0164. Min Act: -0.0005

Data Index: 1423326 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0162. Min Act: -0.0006

Data Index: 221338 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0158. Min Act: -0.0007

Data Index: 717973 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1555988 (Python Code)

Max Activating Token Index: 635

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0157. Min Act: -0.0006

Data Index: 552276 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0154. Min Act: -0.0007

Data Index: 643800 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1335209 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0147. Min Act: -0.0006

Data Index: 722836 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0148. Min Act: -0.0006

Data Index: 351090 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0146. Min Act: -0.0006

Data Index: 282514 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1051192 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0137. Min Act: -0.0006

Data Index: 338313 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1273825 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0145. Min Act: -0.0006

Data Index: 1361924 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1250914 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1504620 (Python Code)

Max Activating Token Index: 620

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1448343 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0138. Min Act: -0.0007

Data Index: 76770 (C4 (Web Text))

Max Activating Token Index: 665