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

Dataset: The Pile

Neuron 177 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8831. Min Range: -7.8831

Max Act: 7.8831. Min Act: -0.0000

Data Index: 1554793 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 7.8831. Min Range: -7.8831

Max Act: 7.3327. Min Act: -0.0000

Data Index: 86606 (The Pile)

Max Activating Token Index: 262

Text #2

Max Range: 7.8831. Min Range: -7.8831

Max Act: 7.3910. Min Act: -0.0000

Data Index: 1003639 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 7.8831. Min Range: -7.8831

Max Act: 7.2933. Min Act: -0.0000

Data Index: 1907195 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 7.8831. Min Range: -7.8831

Max Act: 6.7869. Min Act: -0.0000

Data Index: 335492 (The Pile)

Max Activating Token Index: 273

Text #5

Max Range: 7.8831. Min Range: -7.8831

Max Act: 6.6005. Min Act: -0.0000

Data Index: 1203609 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 7.8831. Min Range: -7.8831

Max Act: 6.4951. Min Act: -0.0000

Data Index: 1656808 (The Pile)

Max Activating Token Index: 243

Text #7

Max Range: 7.8831. Min Range: -7.8831

Max Act: 6.2214. Min Act: -0.0000

Data Index: 655634 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.8656. Min Act: -0.0000

Data Index: 556654 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.9064. Min Act: -0.0000

Data Index: 141494 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.7983. Min Act: -0.0000

Data Index: 1322643 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.8065. Min Act: -0.0000

Data Index: 1558181 (The Pile)

Max Activating Token Index: 307

Text #12

Max Range: 7.8831. Min Range: -7.8831

Max Act: 6.0658. Min Act: -0.0000

Data Index: 264132 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.7345. Min Act: -0.0000

Data Index: 1225817 (The Pile)

Max Activating Token Index: 82

Text #14

Max Range: 7.8831. Min Range: -7.8831

Max Act: 6.2453. Min Act: -0.0000

Data Index: 1415618 (The Pile)

Max Activating Token Index: 506

Text #15

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.7064. Min Act: -0.0000

Data Index: 477776 (The Pile)

Max Activating Token Index: 596

Text #16

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.7746. Min Act: -0.0000

Data Index: 815373 (The Pile)

Max Activating Token Index: 188

Text #17

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.1319. Min Act: -0.0000

Data Index: 1988045 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.5151. Min Act: -0.0000

Data Index: 837479 (The Pile)

Max Activating Token Index: 351

Text #19

Max Range: 7.8831. Min Range: -7.8831

Max Act: 5.4637. Min Act: -0.0000

Data Index: 1607127 (The Pile)

Max Activating Token Index: 911