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

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

Neuron 5085 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: 1.9787. Min Range: -1.9787

Max Act: 1.9787. Min Act: -0.0000

Data Index: 1236414 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.7620. Min Act: -0.0000

Data Index: 84736 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.5151. Min Act: -0.0000

Data Index: 147836 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1219075 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.6040. Min Act: -0.0000

Data Index: 426705 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.5997. Min Act: -0.0000

Data Index: 1332429 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.4292. Min Act: -0.0000

Data Index: 604620 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.5585. Min Act: -0.0000

Data Index: 487883 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.4722. Min Act: -0.0000

Data Index: 195028 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.4468. Min Act: -0.0000

Data Index: 306370 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.4630. Min Act: -0.0000

Data Index: 738339 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.4447. Min Act: -0.0000

Data Index: 826749 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.4375. Min Act: -0.0000

Data Index: 22618 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.3391. Min Act: -0.0000

Data Index: 33566 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.3386. Min Act: -0.0000

Data Index: 554096 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.3409. Min Act: -0.0000

Data Index: 343816 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.3485. Min Act: -0.0000

Data Index: 828857 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.3287. Min Act: -0.0000

Data Index: 251773 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.3245. Min Act: -0.0000

Data Index: 621190 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 1.9787. Min Range: -1.9787

Max Act: 1.3935. Min Act: -0.0000

Data Index: 505013 (C4 (Web Text))

Max Activating Token Index: 243