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

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

Neuron 182 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: 0.0146. Min Range: -0.0146

Max Act: 0.0146. Min Act: -0.0005

Data Index: 1566277 (Python Code)

Max Activating Token Index: 998

Text #1

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1646248 (Python Code)

Max Activating Token Index: 600

Text #2

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0127. Min Act: -0.0005

Data Index: 1460737 (Python Code)

Max Activating Token Index: 541

Text #3

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0119. Min Act: -0.0005

Data Index: 87065 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1639914 (Python Code)

Max Activating Token Index: 522

Text #5

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1628424 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0113. Min Act: -0.0005

Data Index: 489728 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0111. Min Act: -0.0006

Data Index: 372062 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1395688 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0109. Min Act: -0.0005

Data Index: 630973 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0106. Min Act: -0.0005

Data Index: 695722 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0108. Min Act: -0.0005

Data Index: 512890 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1603585 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0105. Min Act: -0.0005

Data Index: 164243 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0106. Min Act: -0.0005

Data Index: 1315560 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1194081 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0107. Min Act: -0.0005

Data Index: 1554164 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0107. Min Act: -0.0005

Data Index: 401412 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0106. Min Act: -0.0006

Data Index: 311172 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0105. Min Act: -0.0005

Data Index: 839633 (C4 (Web Text))

Max Activating Token Index: 3