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

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

Neuron 3185 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0837. Min Range: -6.0837

Max Act: 6.0837. Min Act: -0.0000

Data Index: 371547 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.9877. Min Act: -0.0000

Data Index: 1234761 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.6393. Min Act: -0.0000

Data Index: 1178707 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.6933. Min Act: -0.0000

Data Index: 191932 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.4596. Min Act: -0.0000

Data Index: 834091 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.3860. Min Act: -0.0000

Data Index: 980389 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.1939. Min Act: -0.0000

Data Index: 800767 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.5286. Min Act: -0.0000

Data Index: 274182 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.5107. Min Act: -0.0000

Data Index: 809467 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.6776. Min Act: -0.0000

Data Index: 708350 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.4566. Min Act: -0.0000

Data Index: 970007 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.4187. Min Act: -0.0000

Data Index: 1270042 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.5589. Min Act: -0.0000

Data Index: 1207741 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.3413. Min Act: -0.0000

Data Index: 25236 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.2569. Min Act: -0.0000

Data Index: 713249 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.2196. Min Act: -0.0000

Data Index: 1072193 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.1182. Min Act: -0.0000

Data Index: 1348604 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.1260. Min Act: -0.0000

Data Index: 1258899 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.0972. Min Act: -0.0000

Data Index: 941738 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 6.0837. Min Range: -6.0837

Max Act: 4.0948. Min Act: -0.0000

Data Index: 101959 (C4 (Web Text))

Max Activating Token Index: 476