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

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

Neuron 318 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4141. Min Act: -0.0001

Data Index: 1182546 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4700. Min Act: -0.0001

Data Index: 598325 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4737. Min Act: -0.0001

Data Index: 1077671 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4522. Min Act: -0.0001

Data Index: 768118 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4445. Min Act: -0.0001

Data Index: 428198 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3643. Min Act: -0.0001

Data Index: 826018 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4777. Min Act: -0.0001

Data Index: 733877 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4043. Min Act: -0.0001

Data Index: 785273 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3749. Min Act: -0.0001

Data Index: 4897 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.4025. Min Act: -0.0001

Data Index: 48130 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3841. Min Act: -0.0001

Data Index: 1273479 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3777. Min Act: -0.0001

Data Index: 144841 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3794. Min Act: -0.0001

Data Index: 944062 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3949. Min Act: -0.0001

Data Index: 240709 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3674. Min Act: -0.0001

Data Index: 847874 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3783. Min Act: -0.0001

Data Index: 1180240 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.2979. Min Act: -0.0001

Data Index: 1294412 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3768. Min Act: -0.0001

Data Index: 1013166 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3298. Min Act: -0.0001

Data Index: 664307 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.4777. Min Range: -0.4777

Max Act: 0.3782. Min Act: -0.0001

Data Index: 39881 (C4 (Web Text))

Max Activating Token Index: 104