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

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

Neuron 331 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2272. Min Act: -0.0001

Data Index: 190944 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2405. Min Act: -0.0001

Data Index: 35167 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2291. Min Act: -0.0000

Data Index: 938871 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2373. Min Act: -0.0000

Data Index: 228668 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2156. Min Act: -0.0000

Data Index: 387918 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2223. Min Act: -0.0000

Data Index: 73821 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2188. Min Act: -0.0001

Data Index: 704904 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2015. Min Act: -0.0000

Data Index: 508354 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2187. Min Act: -0.0001

Data Index: 1127864 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2078. Min Act: -0.0000

Data Index: 935948 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2242. Min Act: -0.0000

Data Index: 538038 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2017. Min Act: -0.0001

Data Index: 879010 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1084091 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2000. Min Act: -0.0000

Data Index: 49134 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1969. Min Act: -0.0000

Data Index: 46699 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2079. Min Act: -0.0001

Data Index: 90600 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1022919 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1838. Min Act: -0.0000

Data Index: 505067 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1895. Min Act: -0.0000

Data Index: 596244 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1960. Min Act: -0.0001

Data Index: 393796 (C4 (Web Text))

Max Activating Token Index: 729