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

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

Neuron 2183 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.8761. Min Act: -0.0001

Data Index: 183111 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.8694. Min Act: -0.0001

Data Index: 976440 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.9127. Min Act: -0.0001

Data Index: 224413 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.8144. Min Act: -0.0001

Data Index: 811221 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.8056. Min Act: -0.0001

Data Index: 1102250 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7606. Min Act: -0.0001

Data Index: 1202076 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7628. Min Act: -0.0001

Data Index: 1148560 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7843. Min Act: -0.0001

Data Index: 605248 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7795. Min Act: -0.0001

Data Index: 278207 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7304. Min Act: -0.0001

Data Index: 1067891 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.8021. Min Act: -0.0001

Data Index: 956744 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7723. Min Act: -0.0001

Data Index: 859394 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.6958. Min Act: -0.0001

Data Index: 483003 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7410. Min Act: -0.0001

Data Index: 1320307 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7840. Min Act: -0.0001

Data Index: 387648 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7328. Min Act: -0.0001

Data Index: 461151 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7552. Min Act: -0.0001

Data Index: 368013 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7272. Min Act: -0.0001

Data Index: 639294 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7492. Min Act: -0.0001

Data Index: 1243707 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.9127. Min Range: -0.9127

Max Act: 0.7496. Min Act: -0.0001

Data Index: 347644 (C4 (Web Text))

Max Activating Token Index: 972