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

Dataset: The Pile

Neuron 3415 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: 0.5982. Min Range: -0.5982

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1186609 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.5253. Min Act: -0.0000

Data Index: 536695 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1810040 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.5125. Min Act: -0.0000

Data Index: 669546 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.5049. Min Act: -0.0000

Data Index: 603840 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1716436 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1110343 (The Pile)

Max Activating Token Index: 834

Text #7

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1811428 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4608. Min Act: -0.0000

Data Index: 920111 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1889177 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1246207 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4743. Min Act: -0.0000

Data Index: 151016 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4751. Min Act: -0.0000

Data Index: 108435 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4408. Min Act: -0.0000

Data Index: 897016 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4779. Min Act: -0.0000

Data Index: 672951 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1225505 (The Pile)

Max Activating Token Index: 558

Text #16

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4597. Min Act: -0.0000

Data Index: 442123 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4556. Min Act: -0.0000

Data Index: 98855 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1703668 (The Pile)

Max Activating Token Index: 688

Text #19

Max Range: 0.5982. Min Range: -0.5982

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1183811 (The Pile)

Max Activating Token Index: 35