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

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

Neuron 1864 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: 0.0138. Min Range: -0.0138

Max Act: 0.0138. Min Act: -0.0006

Data Index: 518101 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0125. Min Act: -0.0005

Data Index: 85417 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1072154 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1431282 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0005

Data Index: 242482 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1338995 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1045754 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0117. Min Act: -0.0005

Data Index: 387329 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0005

Data Index: 164089 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0119. Min Act: -0.0005

Data Index: 754913 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1494955 (Python Code)

Max Activating Token Index: 956

Text #11

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0117. Min Act: -0.0005

Data Index: 242617 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0116. Min Act: -0.0006

Data Index: 456776 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0116. Min Act: -0.0005

Data Index: 253921 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0005

Data Index: 600650 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1500052 (Python Code)

Max Activating Token Index: 944

Text #16

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1007148 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1457363 (Python Code)

Max Activating Token Index: 645

Text #18

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1653193 (Python Code)

Max Activating Token Index: 733

Text #19

Max Range: 0.0138. Min Range: -0.0138

Max Act: 0.0112. Min Act: -0.0005

Data Index: 693647 (C4 (Web Text))

Max Activating Token Index: 624