Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4577 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0168. Min Act: -0.0000

Data Index: 534900 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0159. Min Act: -0.0000

Data Index: 1457547 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0160. Min Act: -0.0000

Data Index: 1565171 (Python Code)

Max Activating Token Index: 371

Text #3

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0160. Min Act: -0.0000

Data Index: 1521417 (Python Code)

Max Activating Token Index: 984

Text #4

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0161. Min Act: -0.0000

Data Index: 659707 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0160. Min Act: -0.0000

Data Index: 1551937 (Python Code)

Max Activating Token Index: 50

Text #6

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0173. Min Act: -0.0000

Data Index: 200717 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0153. Min Act: -0.0000

Data Index: 1225869 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0157. Min Act: -0.0000

Data Index: 1586969 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0161. Min Act: -0.0000

Data Index: 1512956 (Python Code)

Max Activating Token Index: 644

Text #10

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1131751 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1252654 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0146. Min Act: -0.0000

Data Index: 669324 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0155. Min Act: -0.0000

Data Index: 996320 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0154. Min Act: -0.0000

Data Index: 163912 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0148. Min Act: -0.0000

Data Index: 886205 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0143. Min Act: -0.0000

Data Index: 1546859 (Python Code)

Max Activating Token Index: 573

Text #17

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1122450 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0147. Min Act: -0.0000

Data Index: 1623488 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 0.0173. Min Range: -0.0173

Max Act: 0.0147. Min Act: -0.0000

Data Index: 1458824 (Python Code)

Max Activating Token Index: 473