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

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

Neuron 506 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: 6.8933. Min Range: -6.8933

Max Act: 6.8217. Min Act: -0.0000

Data Index: 1201478 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 6.8933. Min Range: -6.8933

Max Act: 6.8933. Min Act: -0.0000

Data Index: 656001 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 6.8933. Min Range: -6.8933

Max Act: 6.7633. Min Act: -0.0000

Data Index: 344084 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 6.8933. Min Range: -6.8933

Max Act: 6.6085. Min Act: -0.0000

Data Index: 142546 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 6.8933. Min Range: -6.8933

Max Act: 6.4577. Min Act: -0.0000

Data Index: 562982 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.5775. Min Act: -0.0000

Data Index: 1142730 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.8728. Min Act: -0.0000

Data Index: 528511 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.8274. Min Act: -0.0000

Data Index: 1220999 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.9246. Min Act: -0.0000

Data Index: 1090681 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.8119. Min Act: -0.0000

Data Index: 946960 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.3390. Min Act: -0.0000

Data Index: 719803 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.7973. Min Act: -0.0000

Data Index: 114733 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.3977. Min Act: -0.0000

Data Index: 604092 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.1782. Min Act: -0.0000

Data Index: 97668 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.5521. Min Act: -0.0000

Data Index: 683549 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.8711. Min Act: -0.0000

Data Index: 186682 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.3410. Min Act: -0.0000

Data Index: 959601 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.5227. Min Act: -0.0000

Data Index: 59097 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.3147. Min Act: -0.0000

Data Index: 86599 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 6.8933. Min Range: -6.8933

Max Act: 5.5229. Min Act: -0.0000

Data Index: 1179669 (C4 (Web Text))

Max Activating Token Index: 842