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

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

Neuron 2598 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6157. Min Act: -0.0000

Data Index: 722900 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6300. Min Act: -0.0000

Data Index: 728217 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6587. Min Act: -0.0000

Data Index: 692979 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6271. Min Act: -0.0000

Data Index: 289539 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5933. Min Act: -0.0000

Data Index: 680868 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.6042. Min Act: -0.0000

Data Index: 791382 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1240110 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5695. Min Act: -0.0000

Data Index: 631349 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1350373 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1117474 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5376. Min Act: -0.0000

Data Index: 353057 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1352449 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1609744 (Python Code)

Max Activating Token Index: 968

Text #13

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1271133 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1262090 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5391. Min Act: -0.0000

Data Index: 775039 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5314. Min Act: -0.0000

Data Index: 402004 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5081. Min Act: -0.0000

Data Index: 66262 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.5302. Min Act: -0.0000

Data Index: 282516 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.6587. Min Range: -0.6587

Max Act: 0.4937. Min Act: -0.0000

Data Index: 553552 (C4 (Web Text))

Max Activating Token Index: 178