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

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

Neuron 1577 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.9613. Min Act: -0.0000

Data Index: 1176918 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.8005. Min Act: -0.0000

Data Index: 986898 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.7763. Min Act: -0.0000

Data Index: 214823 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.7593. Min Act: -0.0000

Data Index: 686670 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.9081. Min Act: -0.0000

Data Index: 1045051 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.4421. Min Act: -0.0000

Data Index: 960135 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.6552. Min Act: -0.0000

Data Index: 1073693 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.6286. Min Act: -0.0000

Data Index: 1040741 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.5018. Min Act: -0.0000

Data Index: 112413 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.4815. Min Act: -0.0000

Data Index: 1291987 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.7087. Min Act: -0.0000

Data Index: 738091 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.4637. Min Act: -0.0000

Data Index: 782649 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.4406. Min Act: -0.0000

Data Index: 707681 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.5323. Min Act: -0.0000

Data Index: 1019956 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.4229. Min Act: -0.0000

Data Index: 1316749 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.6661. Min Act: -0.0000

Data Index: 195019 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.6440. Min Act: -0.0000

Data Index: 1006475 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.4620. Min Act: -0.0000

Data Index: 588266 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.4501. Min Act: -0.0000

Data Index: 500774 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 2.9613. Min Range: -2.9613

Max Act: 2.3949. Min Act: -0.0000

Data Index: 128919 (C4 (Web Text))

Max Activating Token Index: 911