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

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

Neuron 1256 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: 0.0131. Min Range: -0.0131

Max Act: 0.0131. Min Act: -0.0006

Data Index: 799257 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0130. Min Act: -0.0006

Data Index: 314092 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0123. Min Act: -0.0006

Data Index: 170020 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0120. Min Act: -0.0006

Data Index: 781157 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0121. Min Act: -0.0005

Data Index: 766962 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0123. Min Act: -0.0006

Data Index: 398348 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0118. Min Act: -0.0005

Data Index: 448615 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0121. Min Act: -0.0006

Data Index: 46483 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0119. Min Act: -0.0005

Data Index: 1261000 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0120. Min Act: -0.0006

Data Index: 366933 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0118. Min Act: -0.0006

Data Index: 433766 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0118. Min Act: -0.0005

Data Index: 621988 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0118. Min Act: -0.0005

Data Index: 289922 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0119. Min Act: -0.0006

Data Index: 860723 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1523168 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0118. Min Act: -0.0005

Data Index: 698242 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1510216 (Python Code)

Max Activating Token Index: 653

Text #17

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0116. Min Act: -0.0006

Data Index: 175302 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0116. Min Act: -0.0006

Data Index: 861001 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0117. Min Act: -0.0006

Data Index: 949793 (C4 (Web Text))

Max Activating Token Index: 466