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

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

Neuron 284 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4324. Min Range: -2.4324

Max Act: 2.4324. Min Act: -0.0000

Data Index: 689023 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 2.4324. Min Range: -2.4324

Max Act: 2.0058. Min Act: -0.0000

Data Index: 1208334 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 2.4324. Min Range: -2.4324

Max Act: 2.0916. Min Act: -0.0000

Data Index: 160044 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 2.4324. Min Range: -2.4324

Max Act: 2.0437. Min Act: -0.0000

Data Index: 355930 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 2.4324. Min Range: -2.4324

Max Act: 2.0521. Min Act: -0.0000

Data Index: 586701 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.9308. Min Act: -0.0000

Data Index: 436898 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 2.4324. Min Range: -2.4324

Max Act: 2.0192. Min Act: -0.0000

Data Index: 76489 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 2.4324. Min Range: -2.4324

Max Act: 2.0143. Min Act: -0.0000

Data Index: 374236 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 2.4324. Min Range: -2.4324

Max Act: 2.0976. Min Act: -0.0000

Data Index: 893739 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.8681. Min Act: -0.0000

Data Index: 930147 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.8894. Min Act: -0.0000

Data Index: 1329664 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.9145. Min Act: -0.0000

Data Index: 260174 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.9923. Min Act: -0.0000

Data Index: 169382 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.8614. Min Act: -0.0000

Data Index: 942180 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 2.4324. Min Range: -2.4324

Max Act: 2.0504. Min Act: -0.0000

Data Index: 884918 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.7964. Min Act: -0.0000

Data Index: 569160 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.8698. Min Act: -0.0000

Data Index: 1350924 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.6873. Min Act: -0.0000

Data Index: 1314942 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.9616. Min Act: -0.0000

Data Index: 376685 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 2.4324. Min Range: -2.4324

Max Act: 1.7733. Min Act: -0.0000

Data Index: 354970 (C4 (Web Text))

Max Activating Token Index: 918