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

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

Neuron 3480 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.2048. Min Act: -0.0000

Data Index: 324490 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1599. Min Act: -0.0001

Data Index: 12215 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1466. Min Act: -0.0001

Data Index: 969884 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1406. Min Act: -0.0000

Data Index: 143333 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1364. Min Act: -0.0001

Data Index: 23113 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1337. Min Act: -0.0001

Data Index: 306766 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1177. Min Act: -0.0000

Data Index: 599887 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1269. Min Act: -0.0000

Data Index: 820298 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1169. Min Act: -0.0001

Data Index: 305280 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1136. Min Act: -0.0001

Data Index: 758810 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1123. Min Act: -0.0000

Data Index: 547790 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1170. Min Act: -0.0001

Data Index: 742208 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1154. Min Act: -0.0000

Data Index: 23485 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1107. Min Act: -0.0001

Data Index: 20095 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1104. Min Act: -0.0000

Data Index: 951766 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1103. Min Act: -0.0001

Data Index: 208405 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1154. Min Act: -0.0000

Data Index: 377725 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.0976. Min Act: -0.0001

Data Index: 89694 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1014. Min Act: -0.0001

Data Index: 695185 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.2048. Min Range: -0.2048

Max Act: 0.1043. Min Act: -0.0001

Data Index: 941249 (C4 (Web Text))

Max Activating Token Index: 799