Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3981 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0148. Min Act: -0.0003

Data Index: 492329 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0141. Min Act: -0.0003

Data Index: 773979 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0121. Min Act: -0.0003

Data Index: 179157 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0117. Min Act: -0.0003

Data Index: 549485 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1154757 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0129. Min Act: -0.0003

Data Index: 106768 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0125. Min Act: -0.0003

Data Index: 293690 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1084910 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0126. Min Act: -0.0004

Data Index: 1173998 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1425227 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1546095 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1378144 (Python Code)

Max Activating Token Index: 802

Text #12

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0111. Min Act: -0.0003

Data Index: 993029 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0120. Min Act: -0.0003

Data Index: 895672 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1362916 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1432242 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0116. Min Act: -0.0003

Data Index: 894146 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0110. Min Act: -0.0003

Data Index: 1020680 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0113. Min Act: -0.0003

Data Index: 1250956 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.0148. Min Range: -0.0148

Max Act: 0.0114. Min Act: -0.0003

Data Index: 711762 (C4 (Web Text))

Max Activating Token Index: 602