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

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

Neuron 3518 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0052. Min Act: -0.0003

Data Index: 273304 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0051. Min Act: -0.0003

Data Index: 476317 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0051. Min Act: -0.0003

Data Index: 880379 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0050. Min Act: -0.0003

Data Index: 95136 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0050. Min Act: -0.0003

Data Index: 1268207 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0048. Min Act: -0.0003

Data Index: 99076 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1189041 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0048. Min Act: -0.0002

Data Index: 784700 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1104604 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1163940 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0048. Min Act: -0.0003

Data Index: 88697 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0047. Min Act: -0.0003

Data Index: 878641 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0047. Min Act: -0.0003

Data Index: 639300 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1266859 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0047. Min Act: -0.0003

Data Index: 809375 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1000881 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0047. Min Act: -0.0003

Data Index: 889950 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0047. Min Act: -0.0003

Data Index: 991369 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0047. Min Act: -0.0003

Data Index: 129008 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.0052. Min Range: -0.0052

Max Act: 0.0047. Min Act: -0.0003

Data Index: 424767 (C4 (Web Text))

Max Activating Token Index: 763