Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2826 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3446. Min Act: -0.0001

Data Index: 1159292 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3549. Min Act: -0.0000

Data Index: 679098 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3384. Min Act: -0.0000

Data Index: 536150 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3246. Min Act: -0.0000

Data Index: 905520 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1281167 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3131. Min Act: -0.0000

Data Index: 589404 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3025. Min Act: -0.0001

Data Index: 1275439 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2944. Min Act: -0.0000

Data Index: 152015 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1359566 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1162491 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2865. Min Act: -0.0000

Data Index: 665869 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2917. Min Act: -0.0000

Data Index: 511037 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1053618 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2870. Min Act: -0.0001

Data Index: 22519 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2747. Min Act: -0.0000

Data Index: 498138 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2740. Min Act: -0.0001

Data Index: 1184620 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1171053 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2643. Min Act: -0.0000

Data Index: 716239 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2830. Min Act: -0.0001

Data Index: 900161 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.3549. Min Range: -0.3549

Max Act: 0.2715. Min Act: -0.0001

Data Index: 483525 (C4 (Web Text))

Max Activating Token Index: 666