Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 445 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.3091. Min Act: -0.0000

Data Index: 22457 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.2095. Min Act: -0.0000

Data Index: 376309 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.2642. Min Act: -0.0000

Data Index: 617982 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0669. Min Act: -0.0000

Data Index: 826706 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0567. Min Act: -0.0000

Data Index: 479697 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0323. Min Act: -0.0000

Data Index: 183257 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0351. Min Act: -0.0000

Data Index: 984772 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0238. Min Act: -0.0000

Data Index: 960437 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1277051 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0630. Min Act: -0.0000

Data Index: 133747 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0011. Min Act: -0.0000

Data Index: 246681 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.9876. Min Act: -0.0000

Data Index: 487055 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.8696. Min Act: -0.0000

Data Index: 962343 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.9554. Min Act: 0.0001

Data Index: 886963 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.9612. Min Act: 0.0001

Data Index: 989538 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.9083. Min Act: -0.0000

Data Index: 209320 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0010. Min Act: -0.0000

Data Index: 726649 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1331054 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.9269. Min Act: -0.0000

Data Index: 16574 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 1.3091. Min Range: -1.3091

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1311742 (C4 (Web Text))

Max Activating Token Index: 63