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

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

Neuron 782 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.6614. Min Act: -0.0000

Data Index: 584831 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.6765. Min Act: -0.0000

Data Index: 454605 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.6807. Min Act: -0.0000

Data Index: 3951 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.5197. Min Act: -0.0000

Data Index: 976919 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.5369. Min Act: -0.0000

Data Index: 1345015 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.3478. Min Act: -0.0001

Data Index: 583072 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.2528. Min Act: -0.0000

Data Index: 456203 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.4069. Min Act: -0.0001

Data Index: 468131 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.3394. Min Act: -0.0000

Data Index: 400310 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.3352. Min Act: -0.0000

Data Index: 827176 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.4311. Min Act: -0.0001

Data Index: 204588 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.2539. Min Act: -0.0000

Data Index: 471686 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.3778. Min Act: -0.0001

Data Index: 846754 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.2521. Min Act: -0.0000

Data Index: 1210713 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.1978. Min Act: -0.0001

Data Index: 240179 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.2230. Min Act: -0.0000

Data Index: 211623 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.1285. Min Act: -0.0000

Data Index: 1182746 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.1979. Min Act: -0.0000

Data Index: 357599 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 2.6807. Min Range: -2.6807

Max Act: 1.9721. Min Act: -0.0000

Data Index: 252502 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 2.6807. Min Range: -2.6807

Max Act: 2.0953. Min Act: -0.0000

Data Index: 879877 (C4 (Web Text))

Max Activating Token Index: 902