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

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

Neuron 1639 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0005

Data Index: 606682 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0193. Min Act: -0.0005

Data Index: 1026040 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0183. Min Act: -0.0005

Data Index: 717900 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0183. Min Act: -0.0005

Data Index: 699980 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0181. Min Act: -0.0005

Data Index: 1333205 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1285886 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0167. Min Act: -0.0005

Data Index: 713328 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0156. Min Act: -0.0005

Data Index: 528080 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0140. Min Act: -0.0006

Data Index: 487210 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1404088 (Python Code)

Max Activating Token Index: 225

Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0133. Min Act: -0.0005

Data Index: 1460821 (Python Code)

Max Activating Token Index: 158

Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0130. Min Act: -0.0006

Data Index: 479313 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1004386 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0123. Min Act: -0.0005

Data Index: 573732 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0121. Min Act: -0.0005

Data Index: 458168 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0123. Min Act: -0.0005

Data Index: 460011 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1649624 (Python Code)

Max Activating Token Index: 460

Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1033125 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0121. Min Act: -0.0005

Data Index: 444317 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1387004 (Python Code)

Max Activating Token Index: 997