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

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

Neuron 96 in Layer 1

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: 80163 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0114. Min Act: -0.0006

Data Index: 442381 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0115. Min Act: -0.0006

Data Index: 306238 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0117. Min Act: -0.0006

Data Index: 833124 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0114. Min Act: -0.0006

Data Index: 104396 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0107. Min Act: -0.0006

Data Index: 245704 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1318228 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0110. Min Act: -0.0006

Data Index: 165785 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1338000 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0105. Min Act: -0.0006

Data Index: 847713 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0104. Min Act: -0.0006

Data Index: 187394 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0104. Min Act: -0.0006

Data Index: 660475 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0103. Min Act: -0.0006

Data Index: 125672 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0103. Min Act: -0.0006

Data Index: 10376 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1171202 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0100. Min Act: -0.0006

Data Index: 176246 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1122937 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1186101 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0103. Min Act: -0.0006

Data Index: 175353 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1357560 (C4 (Web Text))

Max Activating Token Index: 906