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

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

Neuron 376 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4987. Min Act: -0.0001

Data Index: 275060 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.4566. Min Act: -0.0001

Data Index: 227833 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3770. Min Act: -0.0001

Data Index: 1576776 (Python Code)

Max Activating Token Index: 799

Text #3

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3138. Min Act: -0.0001

Data Index: 1427584 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1281501 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1566202 (Python Code)

Max Activating Token Index: 867

Text #6

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3835. Min Act: -0.0001

Data Index: 1596719 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3365. Min Act: -0.0000

Data Index: 455850 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1441704 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1319994 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1360622 (Python Code)

Max Activating Token Index: 366

Text #11

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3087. Min Act: -0.0000

Data Index: 552471 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3537. Min Act: -0.0001

Data Index: 1474362 (Python Code)

Max Activating Token Index: 949

Text #13

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3051. Min Act: -0.0000

Data Index: 526580 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3242. Min Act: -0.0001

Data Index: 1148040 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3034. Min Act: -0.0000

Data Index: 601244 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1056817 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.2663. Min Act: -0.0001

Data Index: 1413787 (Python Code)

Max Activating Token Index: 974

Text #18

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.2960. Min Act: -0.0001

Data Index: 1654791 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 0.4987. Min Range: -0.4987

Max Act: 0.2859. Min Act: -0.0000

Data Index: 342388 (C4 (Web Text))

Max Activating Token Index: 807