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

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

Neuron 8 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.8921. Min Act: -0.0000

Data Index: 57634 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.8124. Min Act: -0.0000

Data Index: 345665 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1350982 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.8423. Min Act: -0.0000

Data Index: 330388 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1148629 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.6632. Min Act: -0.0000

Data Index: 193981 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1147428 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.4724. Min Act: -0.0000

Data Index: 723939 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1163212 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1093647 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.4211. Min Act: -0.0000

Data Index: 254520 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.3230. Min Act: -0.0000

Data Index: 313736 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.3663. Min Act: -0.0000

Data Index: 567458 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.2938. Min Act: -0.0000

Data Index: 892571 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1277221 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1325167 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.2947. Min Act: -0.0000

Data Index: 724474 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1285359 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.2677. Min Act: -0.0000

Data Index: 883462 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.8921. Min Range: -0.8921

Max Act: 0.2844. Min Act: -0.0000

Data Index: 789236 (C4 (Web Text))

Max Activating Token Index: 84