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

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

Neuron 2791 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3987. Min Range: -2.3987

Max Act: 2.3987. Min Act: -0.0000

Data Index: 468511 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.8711. Min Act: -0.0000

Data Index: 1281405 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.9164. Min Act: -0.0000

Data Index: 598716 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.8634. Min Act: -0.0000

Data Index: 1357895 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.8081. Min Act: -0.0000

Data Index: 798410 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 2.3987. Min Range: -2.3987

Max Act: 2.0277. Min Act: -0.0000

Data Index: 187201 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1230188 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.6861. Min Act: -0.0000

Data Index: 1264554 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.6044. Min Act: -0.0000

Data Index: 200237 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.0624. Min Act: -0.0000

Data Index: 536884 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.0476. Min Act: -0.0000

Data Index: 510260 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 2.3987. Min Range: -2.3987

Max Act: 1.0355. Min Act: -0.0000

Data Index: 1256384 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 2.3987. Min Range: -2.3987

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1325009 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 2.3987. Min Range: -2.3987

Max Act: 0.8438. Min Act: -0.0000

Data Index: 91355 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 2.3987. Min Range: -2.3987

Max Act: 0.7911. Min Act: -0.0000

Data Index: 914089 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 2.3987. Min Range: -2.3987

Max Act: 0.8931. Min Act: -0.0000

Data Index: 223091 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 2.3987. Min Range: -2.3987

Max Act: 0.8497. Min Act: -0.0000

Data Index: 603648 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 2.3987. Min Range: -2.3987

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1346006 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 2.3987. Min Range: -2.3987

Max Act: 0.7973. Min Act: -0.0000

Data Index: 193077 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 2.3987. Min Range: -2.3987

Max Act: 0.7869. Min Act: -0.0000

Data Index: 583489 (C4 (Web Text))

Max Activating Token Index: 407