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

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

Neuron 2634 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: 0.4705. Min Range: -0.4705

Max Act: 0.4488. Min Act: -0.0000

Data Index: 474965 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1055428 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4576. Min Act: -0.0000

Data Index: 850584 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4416. Min Act: -0.0000

Data Index: 855348 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4408. Min Act: -0.0000

Data Index: 496687 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1093363 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4453. Min Act: -0.0000

Data Index: 255052 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4229. Min Act: -0.0000

Data Index: 36708 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1027829 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4031. Min Act: -0.0000

Data Index: 849741 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4307. Min Act: -0.0000

Data Index: 667213 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3992. Min Act: -0.0000

Data Index: 572789 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4099. Min Act: -0.0000

Data Index: 502772 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4005. Min Act: -0.0000

Data Index: 57353 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3880. Min Act: -0.0000

Data Index: 99273 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3934. Min Act: -0.0000

Data Index: 935811 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3928. Min Act: -0.0000

Data Index: 619891 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3680. Min Act: -0.0000

Data Index: 344557 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.4027. Min Act: -0.0000

Data Index: 639737 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.4705. Min Range: -0.4705

Max Act: 0.3854. Min Act: -0.0000

Data Index: 889657 (C4 (Web Text))

Max Activating Token Index: 443