Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2192 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.7405. Min Act: -0.0000

Data Index: 380903 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.7903. Min Act: -0.0000

Data Index: 823201 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.6824. Min Act: -0.0000

Data Index: 1084969 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.7189. Min Act: -0.0000

Data Index: 29964 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.6003. Min Act: -0.0000

Data Index: 675288 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.5991. Min Act: -0.0000

Data Index: 359720 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.7737. Min Act: -0.0000

Data Index: 184849 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.4596. Min Act: -0.0000

Data Index: 835195 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.5552. Min Act: -0.0000

Data Index: 411769 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.4566. Min Act: -0.0000

Data Index: 665750 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1032993 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.3332. Min Act: -0.0000

Data Index: 821345 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.3450. Min Act: -0.0000

Data Index: 163723 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.4535. Min Act: -0.0000

Data Index: 781962 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.3618. Min Act: -0.0000

Data Index: 802019 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.2450. Min Act: -0.0000

Data Index: 542178 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.3504. Min Act: -0.0000

Data Index: 590449 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.3069. Min Act: -0.0000

Data Index: 965092 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.3871. Min Act: -0.0000

Data Index: 113501 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 1.7903. Min Range: -1.7903

Max Act: 1.2950. Min Act: -0.0000

Data Index: 130458 (C4 (Web Text))

Max Activating Token Index: 538