Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.8801. Min Act: -0.0001

Data Index: 417316 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.8107. Min Act: -0.0000

Data Index: 554688 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.8660. Min Act: -0.0000

Data Index: 510851 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.7069. Min Act: -0.0000

Data Index: 653951 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.7585. Min Act: -0.0001

Data Index: 749679 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6942. Min Act: -0.0000

Data Index: 111873 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6925. Min Act: -0.0000

Data Index: 567300 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6961. Min Act: -0.0000

Data Index: 729420 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6931. Min Act: -0.0001

Data Index: 1310919 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1029511 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5843. Min Act: -0.0001

Data Index: 103437 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6047. Min Act: -0.0000

Data Index: 377895 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6053. Min Act: -0.0001

Data Index: 483794 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5952. Min Act: -0.0001

Data Index: 872699 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5974. Min Act: -0.0000

Data Index: 128225 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5462. Min Act: -0.0001

Data Index: 1060624 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1091881 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5948. Min Act: -0.0000

Data Index: 896059 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.6055. Min Act: -0.0001

Data Index: 1337687 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.8801. Min Range: -0.8801

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1217205 (C4 (Web Text))

Max Activating Token Index: 342