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

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

Neuron 1407 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.9643. Min Act: -0.0000

Data Index: 829972 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.9220. Min Act: -0.0000

Data Index: 110900 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1181753 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.7133. Min Act: -0.0000

Data Index: 776965 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1128693 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6968. Min Act: -0.0000

Data Index: 672293 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6686. Min Act: -0.0000

Data Index: 280596 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6283. Min Act: -0.0000

Data Index: 673669 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6498. Min Act: -0.0000

Data Index: 415354 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6012. Min Act: -0.0000

Data Index: 830787 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6045. Min Act: -0.0000

Data Index: 969377 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.5942. Min Act: -0.0000

Data Index: 328099 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1026842 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1222754 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6109. Min Act: -0.0000

Data Index: 965548 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6281. Min Act: -0.0000

Data Index: 166405 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1057369 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.6071. Min Act: -0.0000

Data Index: 999423 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1326684 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.9643. Min Range: -0.9643

Max Act: 0.5931. Min Act: -0.0000

Data Index: 301166 (C4 (Web Text))

Max Activating Token Index: 836