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

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

Neuron 4524 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1049583 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5188. Min Act: -0.0000

Data Index: 669456 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5337. Min Act: -0.0000

Data Index: 250642 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1617582 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1582717 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1244508 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1615239 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3977. Min Act: -0.0000

Data Index: 998853 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1398011 (Python Code)

Max Activating Token Index: 527

Text #9

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3606. Min Act: -0.0000

Data Index: 596126 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3449. Min Act: -0.0000

Data Index: 783886 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1258410 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1170102 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1284196 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1478546 (Python Code)

Max Activating Token Index: 245

Text #15

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1009808 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1385515 (Python Code)

Max Activating Token Index: 112

Text #17

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3027. Min Act: -0.0000

Data Index: 895551 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3049. Min Act: -0.0000

Data Index: 358267 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1535867 (Python Code)

Max Activating Token Index: 1004