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

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

Neuron 1160 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1277302 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0147. Min Act: -0.0006

Data Index: 965861 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0143. Min Act: -0.0007

Data Index: 687824 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0143. Min Act: -0.0005

Data Index: 1436211 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0140. Min Act: -0.0006

Data Index: 1254104 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0142. Min Act: -0.0006

Data Index: 284033 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0006

Data Index: 805046 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1005365 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1190067 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1473221 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1557780 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1356838 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1512591 (Python Code)

Max Activating Token Index: 232

Text #13

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1354196 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0136. Min Act: -0.0005

Data Index: 1511981 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0006

Data Index: 533174 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1011471 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0006

Data Index: 576249 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0132. Min Act: -0.0006

Data Index: 914500 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.0153. Min Range: -0.0153

Max Act: 0.0133. Min Act: -0.0005

Data Index: 1384905 (Python Code)

Max Activating Token Index: 14