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

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

Neuron 2255 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: 1426806 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1127091 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0155. Min Act: -0.0002

Data Index: 130900 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1588083 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1418259 (Python Code)

Max Activating Token Index: 383

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1131689 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0148. Min Act: -0.0002

Data Index: 374090 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0148. Min Act: -0.0002

Data Index: 640995 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1420902 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 27606 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1562804 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0144. Min Act: -0.0002

Data Index: 34098 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1603932 (Python Code)

Max Activating Token Index: 34

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0143. Min Act: -0.0002

Data Index: 361125 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1533784 (Python Code)

Max Activating Token Index: 168

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0142. Min Act: -0.0002

Data Index: 994670 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1376187 (Python Code)

Max Activating Token Index: 616

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0141. Min Act: -0.0002

Data Index: 1365991 (Python Code)

Max Activating Token Index: 382

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1393466 (Python Code)

Max Activating Token Index: 72

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1331303 (C4 (Web Text))

Max Activating Token Index: 436