Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.3617. Min Act: -0.0000

Data Index: 8239 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1133579 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.1881. Min Act: -0.0000

Data Index: 485154 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.9709. Min Act: -0.0000

Data Index: 363468 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.0419. Min Act: -0.0001

Data Index: 256281 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.9628. Min Act: -0.0000

Data Index: 813743 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.9088. Min Act: -0.0000

Data Index: 634112 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7206. Min Act: -0.0000

Data Index: 65600 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1093144 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.8823. Min Act: -0.0001

Data Index: 1240691 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7042. Min Act: -0.0000

Data Index: 748608 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1332682 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.8425. Min Act: -0.0000

Data Index: 999992 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7968. Min Act: -0.0000

Data Index: 503313 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.8160. Min Act: -0.0001

Data Index: 510875 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.8921. Min Act: -0.0001

Data Index: 637011 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7666. Min Act: -0.0001

Data Index: 36324 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1236410 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1057266 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 1.3617. Min Range: -1.3617

Max Act: 0.7443. Min Act: -0.0000

Data Index: 520809 (C4 (Web Text))

Max Activating Token Index: 468