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

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

Neuron 1278 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2028. Min Range: -1.2028

Max Act: 1.2028. Min Act: -0.0000

Data Index: 191390 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 1.2028. Min Range: -1.2028

Max Act: 1.0533. Min Act: -0.0000

Data Index: 343990 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.9160. Min Act: -0.0000

Data Index: 983174 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.9720. Min Act: -0.0000

Data Index: 345551 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.8885. Min Act: -0.0000

Data Index: 313114 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.7625. Min Act: -0.0000

Data Index: 882099 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.8543. Min Act: -0.0000

Data Index: 587956 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.7329. Min Act: -0.0000

Data Index: 84100 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1148944 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1296465 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.7440. Min Act: -0.0000

Data Index: 785312 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.7289. Min Act: -0.0000

Data Index: 453971 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.6921. Min Act: -0.0000

Data Index: 1209727 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.6904. Min Act: -0.0001

Data Index: 1211220 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1158653 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.7369. Min Act: -0.0000

Data Index: 87280 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.6176. Min Act: -0.0000

Data Index: 105897 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.6748. Min Act: -0.0000

Data Index: 483990 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1131765 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.2028. Min Range: -1.2028

Max Act: 0.6295. Min Act: -0.0000

Data Index: 61826 (C4 (Web Text))

Max Activating Token Index: 375