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

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

Neuron 77 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: 0.0141. Min Range: -0.0141

Max Act: 0.0141. Min Act: -0.0005

Data Index: 1232722 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0005

Data Index: 1406389 (Python Code)

Max Activating Token Index: 91

Text #2

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0129. Min Act: -0.0005

Data Index: 929432 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0125. Min Act: -0.0005

Data Index: 373220 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0124. Min Act: -0.0005

Data Index: 920199 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0127. Min Act: -0.0005

Data Index: 105997 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0126. Min Act: -0.0005

Data Index: 218059 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0125. Min Act: -0.0005

Data Index: 205638 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1599957 (Python Code)

Max Activating Token Index: 236

Text #9

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0123. Min Act: -0.0005

Data Index: 797548 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0125. Min Act: -0.0005

Data Index: 247291 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1396806 (Python Code)

Max Activating Token Index: 602

Text #12

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1010777 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1469592 (Python Code)

Max Activating Token Index: 810

Text #14

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1050367 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0124. Min Act: -0.0005

Data Index: 83885 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0120. Min Act: -0.0005

Data Index: 177957 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1420482 (Python Code)

Max Activating Token Index: 195

Text #18

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1389819 (Python Code)

Max Activating Token Index: 231

Text #19

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1594628 (Python Code)

Max Activating Token Index: 453