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

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

Neuron 167 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: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 498364 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1524419 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 166475 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1173044 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 547898 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1196886 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1045438 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 533633 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 591119 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 1093621 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 680640 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 442077 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 588030 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 108758 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0138. Min Act: -0.0002

Data Index: 409662 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0136. Min Act: -0.0002

Data Index: 350907 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0136. Min Act: -0.0002

Data Index: 321210 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0136. Min Act: -0.0002

Data Index: 967374 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0136. Min Act: -0.0002

Data Index: 581576 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0137. Min Act: -0.0002

Data Index: 392811 (C4 (Web Text))

Max Activating Token Index: 128