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

Dataset: The Pile

Neuron 787 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1581035 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1141536 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7959. Min Act: -0.0000

Data Index: 977383 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1180684 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7844. Min Act: -0.0000

Data Index: 860182 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7325. Min Act: -0.0000

Data Index: 902223 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1113874 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1239987 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7431. Min Act: -0.0000

Data Index: 370991 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1320152 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1933497 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1253222 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7168. Min Act: -0.0000

Data Index: 1017856 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1718469 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1848970 (The Pile)

Max Activating Token Index: 108

Text #15

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6650. Min Act: -0.0000

Data Index: 697810 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1875692 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1206631 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1641056 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 0.8471. Min Range: -0.8471

Max Act: 0.6764. Min Act: -0.0000

Data Index: 469123 (The Pile)

Max Activating Token Index: 638