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

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

Neuron 630 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7970. Min Act: -0.0000

Data Index: 697632 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7326. Min Act: -0.0000

Data Index: 1113000 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.5886. Min Act: -0.0000

Data Index: 1018328 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.5227. Min Act: -0.0000

Data Index: 363439 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.4440. Min Act: -0.0000

Data Index: 576314 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1367589 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.4298. Min Act: -0.0000

Data Index: 914328 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2546. Min Act: -0.0000

Data Index: 192724 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2994. Min Act: -0.0000

Data Index: 624105 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2926. Min Act: -0.0000

Data Index: 364224 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2787. Min Act: -0.0000

Data Index: 534223 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2811. Min Act: -0.0000

Data Index: 236519 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1206202 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2053. Min Act: -0.0000

Data Index: 353041 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1400. Min Act: -0.0000

Data Index: 767301 (C4 (Web Text))

Max Activating Token Index: 207

Text #15

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2031. Min Act: -0.0000

Data Index: 432207 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2519. Min Act: -0.0000

Data Index: 644604 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2405. Min Act: -0.0000

Data Index: 1113822 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1531. Min Act: -0.0000

Data Index: 412159 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1546. Min Act: -0.0000

Data Index: 311454 (C4 (Web Text))

Max Activating Token Index: 1021