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

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

Neuron 962 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1460632 (Python Code)

Max Activating Token Index: 1004

Text #1

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1576014 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1543396 (Python Code)

Max Activating Token Index: 1016

Text #3

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1651085 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1423568 (Python Code)

Max Activating Token Index: 1008

Text #5

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1503637 (Python Code)

Max Activating Token Index: 438

Text #6

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1646688 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1610119 (Python Code)

Max Activating Token Index: 83

Text #8

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0137. Min Act: -0.0003

Data Index: 446541 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1402621 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1597100 (Python Code)

Max Activating Token Index: 613

Text #11

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1523586 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1380623 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1390407 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1469401 (Python Code)

Max Activating Token Index: 236

Text #15

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1530741 (Python Code)

Max Activating Token Index: 200

Text #16

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1363301 (Python Code)

Max Activating Token Index: 802

Text #17

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1440249 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0137. Min Act: -0.0002

Data Index: 1445475 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1386130 (Python Code)

Max Activating Token Index: 57