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

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

Neuron 3630 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3989. Min Act: -0.0002

Data Index: 471543 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3796. Min Act: -0.0002

Data Index: 100821 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3303. Min Act: -0.0002

Data Index: 309036 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3078. Min Act: -0.0002

Data Index: 868583 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3084. Min Act: -0.0002

Data Index: 516799 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3459. Min Act: -0.0002

Data Index: 74222 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2871. Min Act: -0.0002

Data Index: 32558 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2892. Min Act: -0.0002

Data Index: 1286518 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2854. Min Act: -0.0002

Data Index: 518965 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2609. Min Act: -0.0002

Data Index: 511976 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2931. Min Act: -0.0002

Data Index: 99738 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3033. Min Act: -0.0002

Data Index: 1238099 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2787. Min Act: -0.0002

Data Index: 839841 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2789. Min Act: -0.0002

Data Index: 1187950 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2257. Min Act: -0.0002

Data Index: 1079752 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2283. Min Act: -0.0002

Data Index: 598420 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2819. Min Act: -0.0002

Data Index: 427949 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2102. Min Act: -0.0002

Data Index: 272779 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1903. Min Act: -0.0002

Data Index: 663494 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1708. Min Act: -0.0002

Data Index: 343865 (C4 (Web Text))

Max Activating Token Index: 387