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

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

Neuron 1474 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4705. Min Range: -3.4705

Max Act: 3.4705. Min Act: -0.0001

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 3.4705. Min Range: -3.4705

Max Act: 3.0394. Min Act: -0.0001

Data Index: 1043828 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.4705. Min Range: -3.4705

Max Act: 3.1540. Min Act: -0.0001

Data Index: 788864 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 3.4705. Min Range: -3.4705

Max Act: 2.5713. Min Act: -0.0001

Data Index: 756230 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.4705. Min Range: -3.4705

Max Act: 2.6810. Min Act: -0.0001

Data Index: 33870 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 3.4705. Min Range: -3.4705

Max Act: 2.2968. Min Act: -0.0001

Data Index: 421141 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 3.4705. Min Range: -3.4705

Max Act: 2.5743. Min Act: -0.0001

Data Index: 578881 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 3.4705. Min Range: -3.4705

Max Act: 2.1215. Min Act: -0.0001

Data Index: 723070 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.6910. Min Act: -0.0001

Data Index: 1163590 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.9565. Min Act: -0.0001

Data Index: 562353 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.8891. Min Act: -0.0001

Data Index: 863042 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.7864. Min Act: -0.0001

Data Index: 281432 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.6989. Min Act: -0.0001

Data Index: 600634 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.9286. Min Act: -0.0001

Data Index: 1012298 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.5607. Min Act: -0.0001

Data Index: 140435 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.6006. Min Act: -0.0001

Data Index: 981713 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.6819. Min Act: -0.0001

Data Index: 317349 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.5714. Min Act: -0.0001

Data Index: 878552 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.5868. Min Act: -0.0001

Data Index: 920197 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 3.4705. Min Range: -3.4705

Max Act: 1.4930. Min Act: -0.0001

Data Index: 711425 (C4 (Web Text))

Max Activating Token Index: 699