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

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

Neuron 4210 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: 3.0857. Min Range: -3.0857

Max Act: 3.0005. Min Act: -0.0000

Data Index: 1591836 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 3.0857. Min Range: -3.0857

Max Act: 3.0857. Min Act: -0.0000

Data Index: 1039614 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.8708. Min Act: -0.0000

Data Index: 73987 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.7997. Min Act: -0.0000

Data Index: 160915 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.7861. Min Act: -0.0000

Data Index: 888393 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.7314. Min Act: -0.0000

Data Index: 109369 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.6984. Min Act: -0.0000

Data Index: 1344763 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.6877. Min Act: -0.0000

Data Index: 1127832 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.6981. Min Act: -0.0000

Data Index: 1034120 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.9054. Min Act: -0.0000

Data Index: 1457986 (Python Code)

Max Activating Token Index: 252

Text #10

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.7979. Min Act: -0.0000

Data Index: 656088 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.5264. Min Act: -0.0000

Data Index: 360549 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.6542. Min Act: -0.0000

Data Index: 1136984 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.5972. Min Act: -0.0000

Data Index: 409365 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.2236. Min Act: -0.0000

Data Index: 1319231 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.4666. Min Act: -0.0000

Data Index: 596858 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.6509. Min Act: -0.0000

Data Index: 762639 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.5076. Min Act: -0.0000

Data Index: 1029027 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.3878. Min Act: -0.0000

Data Index: 1240935 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 3.0857. Min Range: -3.0857

Max Act: 2.5127. Min Act: -0.0000

Data Index: 410898 (C4 (Web Text))

Max Activating Token Index: 590