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

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

Neuron 3104 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.4855. Min Act: -0.0000

Data Index: 92582 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.3032. Min Act: 0.0000

Data Index: 407765 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.3057. Min Act: 0.0000

Data Index: 160392 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.0060. Min Act: -0.0000

Data Index: 885065 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.2160. Min Act: -0.0000

Data Index: 94807 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.2006. Min Act: -0.0000

Data Index: 332216 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.0699. Min Act: 0.0000

Data Index: 870026 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.0251. Min Act: -0.0000

Data Index: 89091 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.1166. Min Act: -0.0000

Data Index: 277937 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.0958. Min Act: -0.0000

Data Index: 779979 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 2.4855. Min Range: -2.4855

Max Act: 1.9477. Min Act: 0.0000

Data Index: 272744 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.1077. Min Act: -0.0000

Data Index: 799141 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 2.4855. Min Range: -2.4855

Max Act: 2.0089. Min Act: -0.0000

Data Index: 916513 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.4855. Min Range: -2.4855

Max Act: 1.8614. Min Act: -0.0000

Data Index: 101518 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 2.4855. Min Range: -2.4855

Max Act: 1.8579. Min Act: -0.0000

Data Index: 927438 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 2.4855. Min Range: -2.4855

Max Act: 1.8698. Min Act: -0.0000

Data Index: 791771 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 2.4855. Min Range: -2.4855

Max Act: 1.8982. Min Act: -0.0000

Data Index: 227332 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 2.4855. Min Range: -2.4855

Max Act: 1.9628. Min Act: -0.0000

Data Index: 53152 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 2.4855. Min Range: -2.4855

Max Act: 1.8455. Min Act: -0.0000

Data Index: 492100 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 2.4855. Min Range: -2.4855

Max Act: 1.7278. Min Act: -0.0000

Data Index: 1335204 (C4 (Web Text))

Max Activating Token Index: 788