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

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

Neuron 551 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: 0.0118. Min Range: -0.0118

Max Act: 0.0117. Min Act: -0.0006

Data Index: 121412 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0118. Min Act: -0.0006

Data Index: 222160 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0113. Min Act: -0.0006

Data Index: 406047 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0110. Min Act: -0.0006

Data Index: 104378 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0109. Min Act: -0.0006

Data Index: 813207 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0109. Min Act: -0.0006

Data Index: 748221 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1385661 (Python Code)

Max Activating Token Index: 393

Text #7

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0105. Min Act: -0.0006

Data Index: 593760 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1230222 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1020087 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 982984 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 417902 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0107. Min Act: -0.0006

Data Index: 22450 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0106. Min Act: -0.0006

Data Index: 512603 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 61803 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0107. Min Act: -0.0006

Data Index: 389377 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 486968 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1316784 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0100. Min Act: -0.0006

Data Index: 528878 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.0118. Min Range: -0.0118

Max Act: 0.0103. Min Act: -0.0006

Data Index: 21821 (C4 (Web Text))

Max Activating Token Index: 11