Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2992 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9882. Min Act: -0.0001

Data Index: 995698 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.8176. Min Act: -0.0001

Data Index: 1080114 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.9142. Min Act: -0.0001

Data Index: 888060 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.4954. Min Act: -0.0001

Data Index: 896640 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.5907. Min Act: -0.0001

Data Index: 190488 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1928. Min Act: -0.0001

Data Index: 858188 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1909. Min Act: -0.0001

Data Index: 72027 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.2653. Min Act: -0.0001

Data Index: 29142 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1386. Min Act: -0.0001

Data Index: 342001 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1569. Min Act: -0.0001

Data Index: 1345157 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1498. Min Act: -0.0001

Data Index: 93238 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1267. Min Act: -0.0001

Data Index: 666388 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1615. Min Act: -0.0001

Data Index: 1056744 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.1154. Min Act: -0.0001

Data Index: 783908 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0560. Min Act: -0.0001

Data Index: 324238 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0763. Min Act: -0.0001

Data Index: 143233 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0453. Min Act: -0.0001

Data Index: 76962 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0755. Min Act: -0.0001

Data Index: 208155 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0067. Min Act: -0.0001

Data Index: 336467 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.9882. Min Range: -1.9882

Max Act: 1.0594. Min Act: -0.0001

Data Index: 413833 (C4 (Web Text))

Max Activating Token Index: 220