Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2506 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.4048. Min Act: -0.0001

Data Index: 1646677 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3555. Min Act: -0.0001

Data Index: 1454967 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1397395 (Python Code)

Max Activating Token Index: 398

Text #3

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3607. Min Act: -0.0001

Data Index: 1624970 (Python Code)

Max Activating Token Index: 356

Text #4

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3641. Min Act: -0.0001

Data Index: 1579361 (Python Code)

Max Activating Token Index: 57

Text #5

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3346. Min Act: -0.0001

Data Index: 1415428 (Python Code)

Max Activating Token Index: 989

Text #6

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1375242 (Python Code)

Max Activating Token Index: 682

Text #7

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3492. Min Act: -0.0001

Data Index: 1482223 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3212. Min Act: -0.0001

Data Index: 1574422 (Python Code)

Max Activating Token Index: 830

Text #9

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1409870 (Python Code)

Max Activating Token Index: 736

Text #10

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1463809 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2931. Min Act: -0.0001

Data Index: 1503581 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3251. Min Act: -0.0001

Data Index: 1560012 (Python Code)

Max Activating Token Index: 416

Text #13

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3017. Min Act: -0.0001

Data Index: 1465922 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3033. Min Act: -0.0001

Data Index: 1445263 (Python Code)

Max Activating Token Index: 364

Text #15

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.3112. Min Act: -0.0001

Data Index: 1617122 (Python Code)

Max Activating Token Index: 973

Text #16

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2757. Min Act: -0.0001

Data Index: 1370441 (Python Code)

Max Activating Token Index: 351

Text #17

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2868. Min Act: -0.0001

Data Index: 1422233 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2973. Min Act: -0.0001

Data Index: 1617773 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 0.4048. Min Range: -0.4048

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1600597 (Python Code)

Max Activating Token Index: 967