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

Dataset: The Pile

Neuron 4104 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.6158. Min Act: -0.0000

Data Index: 375621 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1863400 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1883461 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5534. Min Act: -0.0000

Data Index: 39164 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1928476 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.6044. Min Act: 0.0000

Data Index: 214082 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1638064 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5461. Min Act: -0.0000

Data Index: 726240 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1772457 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5899. Min Act: -0.0000

Data Index: 618587 (The Pile)

Max Activating Token Index: 442

Text #10

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1287552 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1601681 (The Pile)

Max Activating Token Index: 232

Text #12

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1919662 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5455. Min Act: -0.0000

Data Index: 160741 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1089284 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5332. Min Act: 0.0000

Data Index: 1388952 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5678. Min Act: -0.0000

Data Index: 233231 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1051675 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1943204 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 0.6158. Min Range: -0.6158

Max Act: 0.5008. Min Act: -0.0000

Data Index: 97352 (The Pile)

Max Activating Token Index: 787