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

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

Neuron 903 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0906. Min Range: -5.0906

Max Act: 5.0906. Min Act: -0.0000

Data Index: 677635 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 5.0906. Min Range: -5.0906

Max Act: 4.9550. Min Act: -0.0000

Data Index: 263977 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 5.0906. Min Range: -5.0906

Max Act: 4.7182. Min Act: -0.0000

Data Index: 1140410 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 5.0906. Min Range: -5.0906

Max Act: 4.7088. Min Act: -0.0000

Data Index: 506095 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 5.0906. Min Range: -5.0906

Max Act: 4.4362. Min Act: -0.0000

Data Index: 1055182 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 5.0906. Min Range: -5.0906

Max Act: 4.0844. Min Act: -0.0000

Data Index: 1202047 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 5.0906. Min Range: -5.0906

Max Act: 4.3914. Min Act: -0.0000

Data Index: 1340039 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.9449. Min Act: -0.0000

Data Index: 488618 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.7665. Min Act: -0.0000

Data Index: 889108 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 5.0906. Min Range: -5.0906

Max Act: 4.3423. Min Act: -0.0000

Data Index: 989621 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.9036. Min Act: -0.0000

Data Index: 1077657 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.4251. Min Act: -0.0000

Data Index: 177591 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.9348. Min Act: -0.0000

Data Index: 968958 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.5739. Min Act: -0.0000

Data Index: 926435 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.4023. Min Act: -0.0000

Data Index: 1313424 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.7230. Min Act: -0.0000

Data Index: 1327108 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.4721. Min Act: -0.0000

Data Index: 950166 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.3401. Min Act: -0.0000

Data Index: 1114310 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.4064. Min Act: -0.0000

Data Index: 1306927 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 5.0906. Min Range: -5.0906

Max Act: 3.3770. Min Act: -0.0000

Data Index: 322222 (C4 (Web Text))

Max Activating Token Index: 835