Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4863 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1240. Min Act: -0.0000

Data Index: 273858 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1112. Min Act: -0.0000

Data Index: 264392 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.1218. Min Act: -0.0000

Data Index: 480646 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0959. Min Act: -0.0001

Data Index: 799881 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1277153 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0960. Min Act: -0.0000

Data Index: 25251 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0927. Min Act: -0.0000

Data Index: 472201 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0956. Min Act: -0.0000

Data Index: 537291 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0878. Min Act: -0.0000

Data Index: 567634 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1175250 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1133904 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0877. Min Act: -0.0000

Data Index: 549949 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0930. Min Act: -0.0001

Data Index: 71069 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1276157 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0788. Min Act: -0.0000

Data Index: 427694 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1303049 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1516137 (Python Code)

Max Activating Token Index: 327

Text #17

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0872. Min Act: -0.0000

Data Index: 864761 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0837. Min Act: -0.0000

Data Index: 916543 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.1240. Min Range: -0.1240

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1182979 (C4 (Web Text))

Max Activating Token Index: 835