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

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

Neuron 906 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.5747. Min Act: -0.0000

Data Index: 426907 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.5458. Min Act: -0.0000

Data Index: 968059 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.4668. Min Act: -0.0000

Data Index: 625254 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.5088. Min Act: -0.0000

Data Index: 582320 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.4577. Min Act: -0.0000

Data Index: 994778 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.4577. Min Act: -0.0000

Data Index: 12588 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.3976. Min Act: -0.0000

Data Index: 1272820 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.4009. Min Act: -0.0000

Data Index: 719619 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.2801. Min Act: -0.0000

Data Index: 931131 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.3968. Min Act: -0.0000

Data Index: 1296457 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.3532. Min Act: -0.0000

Data Index: 884992 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.3070. Min Act: -0.0000

Data Index: 1058374 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.3260. Min Act: -0.0000

Data Index: 1104597 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.4048. Min Act: -0.0000

Data Index: 4396 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.2300. Min Act: -0.0000

Data Index: 144840 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.2564. Min Act: -0.0000

Data Index: 348842 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.2155. Min Act: -0.0000

Data Index: 112365 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.2240. Min Act: -0.0000

Data Index: 455028 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.2809. Min Act: -0.0000

Data Index: 1018224 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 1.5747. Min Range: -1.5747

Max Act: 1.1855. Min Act: -0.0000

Data Index: 578320 (C4 (Web Text))

Max Activating Token Index: 351