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

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

Neuron 1943 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: 0.0134. Min Range: -0.0134

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1629778 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0006

Data Index: 1641231 (Python Code)

Max Activating Token Index: 141

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0132. Min Act: -0.0006

Data Index: 1466172 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1644504 (Python Code)

Max Activating Token Index: 339

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1402317 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1575580 (Python Code)

Max Activating Token Index: 163

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1377495 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1422615 (Python Code)

Max Activating Token Index: 313

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0128. Min Act: -0.0005

Data Index: 1570609 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1565921 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0128. Min Act: -0.0006

Data Index: 296805 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1503904 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1494155 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1482464 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1433831 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1421103 (Python Code)

Max Activating Token Index: 220

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1426454 (Python Code)

Max Activating Token Index: 255

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1499536 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1519944 (Python Code)

Max Activating Token Index: 207

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1541101 (Python Code)

Max Activating Token Index: 330