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

Dataset: The Pile

Neuron 3014 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: 1.6034. Min Range: -1.6034

Max Act: 1.6034. Min Act: -0.0000

Data Index: 1823366 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3660. Min Act: -0.0000

Data Index: 1561852 (The Pile)

Max Activating Token Index: 427

Text #2

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3995. Min Act: -0.0000

Data Index: 1382914 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2805. Min Act: -0.0000

Data Index: 315120 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2293. Min Act: -0.0000

Data Index: 841425 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1919770 (The Pile)

Max Activating Token Index: 326

Text #6

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.3091. Min Act: -0.0000

Data Index: 1953031 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1959. Min Act: -0.0000

Data Index: 680761 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2391. Min Act: -0.0000

Data Index: 1485144 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1988. Min Act: -0.0000

Data Index: 84688 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1411793 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1972500 (The Pile)

Max Activating Token Index: 181

Text #12

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1127967 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2278. Min Act: -0.0000

Data Index: 551499 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2162. Min Act: -0.0000

Data Index: 38532 (The Pile)

Max Activating Token Index: 232

Text #15

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2274. Min Act: -0.0000

Data Index: 532656 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2579. Min Act: -0.0000

Data Index: 1208594 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.2100. Min Act: -0.0000

Data Index: 1122106 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1431. Min Act: -0.0000

Data Index: 534436 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 1.6034. Min Range: -1.6034

Max Act: 1.1858. Min Act: -0.0000

Data Index: 427046 (The Pile)

Max Activating Token Index: 445