Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2498 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4932. Min Act: -0.0000

Data Index: 310229 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1346204 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4554. Min Act: -0.0000

Data Index: 557063 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4497. Min Act: -0.0000

Data Index: 566542 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4291. Min Act: -0.0000

Data Index: 514691 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4872. Min Act: -0.0000

Data Index: 461046 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4347. Min Act: -0.0000

Data Index: 263692 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1372897 (Python Code)

Max Activating Token Index: 839

Text #8

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4253. Min Act: -0.0000

Data Index: 365942 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1305988 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4222. Min Act: -0.0000

Data Index: 330187 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3418. Min Act: -0.0000

Data Index: 138331 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1363440 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1234657 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4064. Min Act: -0.0000

Data Index: 270931 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3905. Min Act: -0.0000

Data Index: 592169 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4049. Min Act: -0.0000

Data Index: 871611 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1108176 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3927. Min Act: -0.0000

Data Index: 899516 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1519210 (Python Code)

Max Activating Token Index: 204