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

Dataset: The Pile

Neuron 934 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1687818 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0078. Min Act: -0.0000

Data Index: 652304 (The Pile)

Max Activating Token Index: 391

Text #2

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0160. Min Act: -0.0000

Data Index: 934138 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1611156 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9744. Min Act: -0.0000

Data Index: 630908 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1202809 (The Pile)

Max Activating Token Index: 82

Text #6

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1449225 (The Pile)

Max Activating Token Index: 168

Text #7

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1517573 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1462809 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1258204 (The Pile)

Max Activating Token Index: 975

Text #10

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8132. Min Act: -0.0000

Data Index: 666932 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1857648 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8445. Min Act: -0.0000

Data Index: 932307 (The Pile)

Max Activating Token Index: 176

Text #13

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8396. Min Act: -0.0000

Data Index: 217498 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1258491 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1493043 (The Pile)

Max Activating Token Index: 1013

Text #16

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1477602 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1291124 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1818017 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 1.2816. Min Range: -1.2816

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1269149 (The Pile)

Max Activating Token Index: 868