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

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

Neuron 3218 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5713. Min Range: -3.5713

Max Act: 3.5713. Min Act: -0.0001

Data Index: 892978 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.6614. Min Act: -0.0001

Data Index: 705330 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.6268. Min Act: -0.0001

Data Index: 178627 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.5003. Min Act: -0.0001

Data Index: 249104 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.3006. Min Act: -0.0001

Data Index: 1004260 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.4289. Min Act: -0.0001

Data Index: 789715 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.2004. Min Act: -0.0001

Data Index: 949417 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.3066. Min Act: -0.0001

Data Index: 728215 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.0713. Min Act: -0.0001

Data Index: 677707 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.0541. Min Act: -0.0001

Data Index: 344954 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.1583. Min Act: -0.0001

Data Index: 445947 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 3.5713. Min Range: -3.5713

Max Act: 1.9986. Min Act: -0.0001

Data Index: 286673 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.0566. Min Act: -0.0001

Data Index: 555088 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.0335. Min Act: -0.0000

Data Index: 996546 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.0294. Min Act: -0.0001

Data Index: 324733 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 3.5713. Min Range: -3.5713

Max Act: 2.1292. Min Act: -0.0001

Data Index: 1253928 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 3.5713. Min Range: -3.5713

Max Act: 1.9119. Min Act: -0.0001

Data Index: 1286435 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 3.5713. Min Range: -3.5713

Max Act: 1.7617. Min Act: -0.0001

Data Index: 771311 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 3.5713. Min Range: -3.5713

Max Act: 1.8451. Min Act: -0.0001

Data Index: 564872 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 3.5713. Min Range: -3.5713

Max Act: 1.6514. Min Act: -0.0001

Data Index: 931214 (C4 (Web Text))

Max Activating Token Index: 662