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

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

Neuron 2903 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.9595. Min Act: -0.0000

Data Index: 770781 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.5853. Min Act: -0.0000

Data Index: 1158059 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.5204. Min Act: -0.0000

Data Index: 1171651 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.5815. Min Act: -0.0000

Data Index: 365164 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.2397. Min Act: -0.0000

Data Index: 662463 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.3396. Min Act: -0.0000

Data Index: 125794 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.4499. Min Act: -0.0000

Data Index: 1343702 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.3768. Min Act: -0.0000

Data Index: 1264781 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.3537. Min Act: -0.0000

Data Index: 121520 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.3670. Min Act: -0.0000

Data Index: 355129 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.3579. Min Act: -0.0000

Data Index: 727042 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.0580. Min Act: -0.0000

Data Index: 896185 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.2712. Min Act: -0.0000

Data Index: 411719 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.3735. Min Act: -0.0000

Data Index: 870807 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.2400. Min Act: -0.0000

Data Index: 290551 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.1985. Min Act: -0.0000

Data Index: 950470 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.2217. Min Act: -0.0000

Data Index: 969730 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.0947. Min Act: -0.0000

Data Index: 667475 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.1858. Min Act: -0.0000

Data Index: 1310829 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 2.9595. Min Range: -2.9595

Max Act: 2.1956. Min Act: -0.0000

Data Index: 919638 (C4 (Web Text))

Max Activating Token Index: 16