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

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

Neuron 3303 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.8967. Min Act: -0.0001

Data Index: 282760 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.7092. Min Act: -0.0001

Data Index: 1203246 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.5466. Min Act: -0.0001

Data Index: 283766 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.4879. Min Act: -0.0001

Data Index: 917419 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.4300. Min Act: -0.0001

Data Index: 788848 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.2095. Min Act: -0.0001

Data Index: 1082090 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.3576. Min Act: -0.0001

Data Index: 989712 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.3532. Min Act: -0.0001

Data Index: 671286 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.3088. Min Act: -0.0001

Data Index: 112766 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.4070. Min Act: -0.0001

Data Index: 335196 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.2891. Min Act: -0.0001

Data Index: 165818 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.0859. Min Act: -0.0001

Data Index: 431334 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.1675. Min Act: -0.0001

Data Index: 1076909 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.0888. Min Act: -0.0001

Data Index: 384366 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.2456. Min Act: -0.0001

Data Index: 672844 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.1111. Min Act: -0.0001

Data Index: 380114 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.2162. Min Act: -0.0001

Data Index: 1331136 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.1848. Min Act: -0.0001

Data Index: 1130936 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.2212. Min Act: -0.0001

Data Index: 1241330 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 1.8967. Min Range: -1.8967

Max Act: 1.2050. Min Act: -0.0001

Data Index: 726761 (C4 (Web Text))

Max Activating Token Index: 380