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

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

Neuron 1249 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: 2.7529. Min Range: -2.7529

Max Act: 2.7529. Min Act: -0.0000

Data Index: 1442812 (Python Code)

Max Activating Token Index: 515

Text #1

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.4929. Min Act: -0.0000

Data Index: 1053806 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.5205. Min Act: -0.0000

Data Index: 140342 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.6060. Min Act: -0.0000

Data Index: 1638929 (Python Code)

Max Activating Token Index: 117

Text #4

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.3480. Min Act: -0.0000

Data Index: 1449843 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.4464. Min Act: -0.0000

Data Index: 1536039 (Python Code)

Max Activating Token Index: 894

Text #6

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.4180. Min Act: -0.0000

Data Index: 1645019 (Python Code)

Max Activating Token Index: 166

Text #7

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.2876. Min Act: -0.0000

Data Index: 1392703 (Python Code)

Max Activating Token Index: 452

Text #8

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.2064. Min Act: -0.0000

Data Index: 1402675 (Python Code)

Max Activating Token Index: 151

Text #9

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.4386. Min Act: -0.0000

Data Index: 846582 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.1747. Min Act: -0.0000

Data Index: 1395363 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.2828. Min Act: -0.0000

Data Index: 1221308 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.2792. Min Act: -0.0000

Data Index: 1567510 (Python Code)

Max Activating Token Index: 556

Text #13

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.0609. Min Act: -0.0000

Data Index: 1648135 (Python Code)

Max Activating Token Index: 359

Text #14

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.1111. Min Act: -0.0000

Data Index: 1603727 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.0874. Min Act: -0.0000

Data Index: 1445729 (Python Code)

Max Activating Token Index: 895

Text #16

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.2054. Min Act: -0.0000

Data Index: 263422 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.0931. Min Act: -0.0000

Data Index: 1547731 (Python Code)

Max Activating Token Index: 948

Text #18

Max Range: 2.7529. Min Range: -2.7529

Max Act: 2.0062. Min Act: -0.0000

Data Index: 122997 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 2.7529. Min Range: -2.7529

Max Act: 1.8096. Min Act: -0.0000

Data Index: 1051361 (C4 (Web Text))

Max Activating Token Index: 305