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

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

Neuron 1981 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5935. Min Range: -5.5935

Max Act: 5.5935. Min Act: -0.0001

Data Index: 957618 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 5.5935. Min Range: -5.5935

Max Act: 5.5578. Min Act: -0.0000

Data Index: 1136654 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.7625. Min Act: -0.0000

Data Index: 174967 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.1351. Min Act: -0.0001

Data Index: 336991 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.2385. Min Act: -0.0000

Data Index: 98604 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.3898. Min Act: -0.0001

Data Index: 24650 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.3712. Min Act: -0.0000

Data Index: 552502 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.2757. Min Act: -0.0001

Data Index: 553241 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.4158. Min Act: -0.0000

Data Index: 1136070 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 5.5935. Min Range: -5.5935

Max Act: 3.7792. Min Act: -0.0001

Data Index: 883686 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 5.5935. Min Range: -5.5935

Max Act: 3.9050. Min Act: -0.0000

Data Index: 887803 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.3985. Min Act: -0.0001

Data Index: 655216 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.5505. Min Act: -0.0001

Data Index: 57880 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.2087. Min Act: -0.0001

Data Index: 836579 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.5426. Min Act: -0.0000

Data Index: 715995 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.0044. Min Act: -0.0001

Data Index: 634692 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.2902. Min Act: -0.0001

Data Index: 809275 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.0749. Min Act: -0.0001

Data Index: 307852 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 5.5935. Min Range: -5.5935

Max Act: 3.7153. Min Act: -0.0001

Data Index: 1071104 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 5.5935. Min Range: -5.5935

Max Act: 4.1760. Min Act: -0.0001

Data Index: 380459 (C4 (Web Text))

Max Activating Token Index: 768