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

Dataset: The Pile

Neuron 3655 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.6705. Min Act: -0.0000

Data Index: 1423467 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.5761. Min Act: -0.0000

Data Index: 371202 (The Pile)

Max Activating Token Index: 690

Text #2

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4969. Min Act: -0.0000

Data Index: 228214 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1330536 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4508. Min Act: -0.0000

Data Index: 467744 (The Pile)

Max Activating Token Index: 253

Text #5

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1596928 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4123. Min Act: -0.0000

Data Index: 376338 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1578089 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1809342 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1823071 (The Pile)

Max Activating Token Index: 162

Text #10

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1199120 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1859620 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1034376 (The Pile)

Max Activating Token Index: 676

Text #13

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1974671 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3668. Min Act: -0.0000

Data Index: 604845 (The Pile)

Max Activating Token Index: 193

Text #15

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3658. Min Act: -0.0000

Data Index: 802796 (The Pile)

Max Activating Token Index: 65

Text #16

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3641. Min Act: -0.0000

Data Index: 203601 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1348033 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3622. Min Act: -0.0000

Data Index: 649833 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 0.6705. Min Range: -0.6705

Max Act: 0.3893. Min Act: -0.0000

Data Index: 665558 (The Pile)

Max Activating Token Index: 1011