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

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

Neuron 2902 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4871. Min Act: -0.0000

Data Index: 225189 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1318806 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4558. Min Act: -0.0000

Data Index: 67292 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4678. Min Act: -0.0000

Data Index: 440031 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1001547 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4397. Min Act: -0.0000

Data Index: 544079 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4500. Min Act: -0.0000

Data Index: 298243 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4424. Min Act: -0.0000

Data Index: 816428 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4336. Min Act: -0.0000

Data Index: 225220 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1351472 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1226977 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4223. Min Act: -0.0000

Data Index: 372981 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4303. Min Act: -0.0000

Data Index: 638414 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4140. Min Act: -0.0000

Data Index: 888578 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4273. Min Act: -0.0000

Data Index: 758050 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3914. Min Act: -0.0001

Data Index: 1289137 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1000201 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1006840 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3740. Min Act: -0.0000

Data Index: 999463 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.4871. Min Range: -0.4871

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1301010 (C4 (Web Text))

Max Activating Token Index: 370