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

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

Neuron 3388 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: 0.6666. Min Range: -0.6666

Max Act: 0.6666. Min Act: -0.0000

Data Index: 448509 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1199363 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5482. Min Act: -0.0000

Data Index: 895115 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5977. Min Act: -0.0000

Data Index: 6101 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5358. Min Act: -0.0000

Data Index: 375298 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4917. Min Act: -0.0000

Data Index: 599629 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5475. Min Act: -0.0000

Data Index: 685120 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.6013. Min Act: -0.0000

Data Index: 708800 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4850. Min Act: -0.0000

Data Index: 7059 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1341003 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.5290. Min Act: -0.0000

Data Index: 43820 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4870. Min Act: -0.0000

Data Index: 132044 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4848. Min Act: -0.0000

Data Index: 587280 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4552. Min Act: -0.0000

Data Index: 880345 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1253054 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4216. Min Act: -0.0000

Data Index: 605340 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1211660 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4371. Min Act: -0.0000

Data Index: 93172 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4113. Min Act: -0.0000

Data Index: 88673 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.6666. Min Range: -0.6666

Max Act: 0.4167. Min Act: -0.0000

Data Index: 779374 (C4 (Web Text))

Max Activating Token Index: 867