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

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

Neuron 1882 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0003

Data Index: 24576 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1504668 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1623426 (Python Code)

Max Activating Token Index: 902

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1431723 (Python Code)

Max Activating Token Index: 847

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1532184 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0139. Min Act: -0.0003

Data Index: 1242537 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1484125 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0003

Data Index: 958621 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0132. Min Act: -0.0003

Data Index: 54312 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0137. Min Act: -0.0003

Data Index: 109335 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0137. Min Act: -0.0003

Data Index: 350396 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0138. Min Act: -0.0003

Data Index: 854727 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0003

Data Index: 565179 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0138. Min Act: -0.0003

Data Index: 205110 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0134. Min Act: -0.0003

Data Index: 249809 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1403957 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0133. Min Act: -0.0003

Data Index: 1210279 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0133. Min Act: -0.0003

Data Index: 350269 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1632637 (Python Code)

Max Activating Token Index: 540

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0002

Data Index: 831582 (C4 (Web Text))

Max Activating Token Index: 516