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

Dataset: The Pile

Neuron 1411 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: 1.1083. Min Range: -1.1083

Max Act: 1.1083. Min Act: -0.0000

Data Index: 1037079 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 1.1083. Min Range: -1.1083

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1013943 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1660659 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.9204. Min Act: -0.0000

Data Index: 997093 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1010194 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 1.1083. Min Range: -1.1083

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1847804 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1520176 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1248174 (The Pile)

Max Activating Token Index: 684

Text #8

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8346. Min Act: -0.0000

Data Index: 601755 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8471. Min Act: -0.0000

Data Index: 421586 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.7447. Min Act: -0.0000

Data Index: 1101822 (The Pile)

Max Activating Token Index: 41

Text #11

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8414. Min Act: -0.0000

Data Index: 389925 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1476981 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.7752. Min Act: -0.0000

Data Index: 1540794 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1780276 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.8086. Min Act: -0.0000

Data Index: 903075 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1095121 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.7338. Min Act: -0.0000

Data Index: 816595 (The Pile)

Max Activating Token Index: 408

Text #18

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.7440. Min Act: -0.0000

Data Index: 1208664 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 1.1083. Min Range: -1.1083

Max Act: 0.7174. Min Act: -0.0000

Data Index: 449209 (The Pile)

Max Activating Token Index: 472