Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 964 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.7293. Min Range: -3.7293

Max Act: 3.7293. Min Act: -0.0000

Data Index: 1253306 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.5101. Min Act: -0.0000

Data Index: 1393833 (The Pile)

Max Activating Token Index: 504

Text #2

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.3445. Min Act: -0.0000

Data Index: 141766 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.2112. Min Act: -0.0000

Data Index: 181999 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.3287. Min Act: -0.0000

Data Index: 124866 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.1276. Min Act: -0.0000

Data Index: 134828 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.1908. Min Act: -0.0000

Data Index: 722156 (The Pile)

Max Activating Token Index: 123

Text #7

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.2165. Min Act: -0.0000

Data Index: 661934 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.4224. Min Act: 0.0000

Data Index: 1614329 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.1899. Min Act: -0.0000

Data Index: 740463 (The Pile)

Max Activating Token Index: 465

Text #10

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.1936. Min Act: -0.0000

Data Index: 320991 (The Pile)

Max Activating Token Index: 122

Text #11

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.0144. Min Act: -0.0000

Data Index: 354849 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.2500. Min Act: -0.0000

Data Index: 1209657 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.1071. Min Act: -0.0000

Data Index: 1164667 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.1850. Min Act: -0.0000

Data Index: 1507502 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.0793. Min Act: -0.0000

Data Index: 227534 (The Pile)

Max Activating Token Index: 311

Text #16

Max Range: 3.7293. Min Range: -3.7293

Max Act: 2.1369. Min Act: -0.0000

Data Index: 993919 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 3.7293. Min Range: -3.7293

Max Act: 1.8780. Min Act: -0.0000

Data Index: 1658366 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 3.7293. Min Range: -3.7293

Max Act: 1.8957. Min Act: -0.0000

Data Index: 1639347 (The Pile)

Max Activating Token Index: 66

Text #19

Max Range: 3.7293. Min Range: -3.7293

Max Act: 1.9430. Min Act: -0.0000

Data Index: 1223756 (The Pile)

Max Activating Token Index: 623