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

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

Neuron 1456 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: 0.5975. Min Range: -0.5975

Max Act: 0.5975. Min Act: -0.0001

Data Index: 488870 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.4978. Min Act: -0.0000

Data Index: 267615 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3443. Min Act: -0.0001

Data Index: 461999 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3487. Min Act: -0.0001

Data Index: 654618 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3541. Min Act: -0.0000

Data Index: 883977 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1271970 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3188. Min Act: -0.0001

Data Index: 1141764 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.3194. Min Act: -0.0001

Data Index: 1124964 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2926. Min Act: -0.0001

Data Index: 839557 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2860. Min Act: -0.0001

Data Index: 1344077 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2892. Min Act: -0.0001

Data Index: 18786 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2925. Min Act: -0.0001

Data Index: 882469 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2832. Min Act: -0.0001

Data Index: 821988 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2761. Min Act: -0.0001

Data Index: 841070 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2707. Min Act: -0.0000

Data Index: 332410 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1015156 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2781. Min Act: -0.0001

Data Index: 1339633 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2543. Min Act: -0.0001

Data Index: 954023 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2410. Min Act: -0.0000

Data Index: 973836 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.5975. Min Range: -0.5975

Max Act: 0.2743. Min Act: -0.0000

Data Index: 198519 (C4 (Web Text))

Max Activating Token Index: 634