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

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

Neuron 2952 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: 0.0141. Min Range: -0.0141

Max Act: 0.0141. Min Act: -0.0003

Data Index: 349643 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0003

Data Index: 315171 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0120. Min Act: -0.0003

Data Index: 100328 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1228117 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0105. Min Act: -0.0003

Data Index: 432796 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0111. Min Act: -0.0003

Data Index: 477751 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1097403 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0100. Min Act: -0.0003

Data Index: 406115 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0099. Min Act: -0.0003

Data Index: 1582635 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0095. Min Act: -0.0003

Data Index: 832003 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0098. Min Act: -0.0003

Data Index: 1386478 (Python Code)

Max Activating Token Index: 698

Text #11

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0097. Min Act: -0.0003

Data Index: 562239 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1327046 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1347350 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0094. Min Act: -0.0003

Data Index: 477644 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0098. Min Act: -0.0003

Data Index: 455937 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0093. Min Act: -0.0003

Data Index: 1415136 (Python Code)

Max Activating Token Index: 278

Text #17

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0090. Min Act: -0.0003

Data Index: 576069 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0091. Min Act: -0.0003

Data Index: 753321 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0093. Min Act: -0.0003

Data Index: 840377 (C4 (Web Text))

Max Activating Token Index: 319