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

Dataset: The Pile

Neuron 3786 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.6199. Min Act: -0.0000

Data Index: 117343 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.6550. Min Act: -0.0000

Data Index: 1895164 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1318547 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.5104. Min Act: -0.0000

Data Index: 682890 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.3475. Min Act: -0.0000

Data Index: 761024 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1273969 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.3270. Min Act: -0.0000

Data Index: 1922126 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.3198. Min Act: -0.0000

Data Index: 1684554 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.3916. Min Act: -0.0000

Data Index: 972857 (The Pile)

Max Activating Token Index: 544

Text #9

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1075931 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.3720. Min Act: -0.0000

Data Index: 826065 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.3249. Min Act: -0.0000

Data Index: 64233 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.2778. Min Act: -0.0000

Data Index: 1275725 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.2485. Min Act: -0.0000

Data Index: 1213082 (The Pile)

Max Activating Token Index: 995

Text #14

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.2831. Min Act: -0.0000

Data Index: 367951 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.2079. Min Act: -0.0000

Data Index: 407633 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.2084. Min Act: -0.0000

Data Index: 72775 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.2594. Min Act: -0.0000

Data Index: 580391 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 1.6550. Min Range: -1.6550

Max Act: 1.1562. Min Act: -0.0000

Data Index: 1572087 (The Pile)

Max Activating Token Index: 115

Text #19

Max Range: 1.6550. Min Range: -1.6550

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1810143 (The Pile)

Max Activating Token Index: 280