Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 447 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1406236 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1441446 (Python Code)

Max Activating Token Index: 879

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1425627 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1649934 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1548363 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1472160 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1510425 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1587270 (Python Code)

Max Activating Token Index: 53

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1473666 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1636954 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1445193 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1396195 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0137. Min Act: -0.0001

Data Index: 1452114 (Python Code)

Max Activating Token Index: 734

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1540970 (Python Code)

Max Activating Token Index: 803

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1494779 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1617213 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1509847 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1611663 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1645201 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1519852 (Python Code)

Max Activating Token Index: 12