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

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

Neuron 1172 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4508. Min Range: -5.4508

Max Act: 5.4508. Min Act: -0.0000

Data Index: 232726 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.6094. Min Act: -0.0000

Data Index: 1242670 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.7245. Min Act: -0.0000

Data Index: 939375 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.6762. Min Act: -0.0000

Data Index: 1319248 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.4887. Min Act: -0.0000

Data Index: 615248 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.4282. Min Act: -0.0000

Data Index: 683091 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.4113. Min Act: -0.0000

Data Index: 508282 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.4072. Min Act: -0.0000

Data Index: 1206451 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.1728. Min Act: -0.0000

Data Index: 790088 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.4976. Min Act: -0.0000

Data Index: 1268103 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.1668. Min Act: -0.0000

Data Index: 540534 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.1599. Min Act: -0.0000

Data Index: 450255 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.3318. Min Act: -0.0000

Data Index: 1044131 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 5.4508. Min Range: -5.4508

Max Act: 3.9695. Min Act: -0.0000

Data Index: 825114 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.0964. Min Act: -0.0000

Data Index: 621428 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.2622. Min Act: -0.0000

Data Index: 895274 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.3682. Min Act: -0.0000

Data Index: 230658 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.1600. Min Act: -0.0000

Data Index: 1027014 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.1584. Min Act: -0.0000

Data Index: 1153008 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 5.4508. Min Range: -5.4508

Max Act: 4.1215. Min Act: -0.0000

Data Index: 813591 (C4 (Web Text))

Max Activating Token Index: 204