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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4069 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1351640 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1923. Min Act: -0.0000

Data Index: 950679 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1534. Min Act: -0.0001

Data Index: 1155675 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0502. Min Act: -0.0001

Data Index: 978967 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0186. Min Act: -0.0000

Data Index: 371297 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9501. Min Act: -0.0001

Data Index: 311124 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0103. Min Act: -0.0000

Data Index: 1109535 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9726. Min Act: -0.0001

Data Index: 110376 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0015. Min Act: -0.0000

Data Index: 495042 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9544. Min Act: -0.0000

Data Index: 708069 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9865. Min Act: -0.0000

Data Index: 83184 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1229377 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1276017 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9432. Min Act: -0.0001

Data Index: 77741 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1291966 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1067002 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9412. Min Act: -0.0000

Data Index: 461528 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9312. Min Act: -0.0000

Data Index: 234832 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9052. Min Act: -0.0001

Data Index: 1021523 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 1.3421. Min Range: -1.3421

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1273575 (C4 (Web Text))

Max Activating Token Index: 770