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

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

Neuron 4760 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0089. Min Range: -5.0089

Max Act: 5.0089. Min Act: -0.0000

Data Index: 1040049 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 5.0089. Min Range: -5.0089

Max Act: 4.8960. Min Act: -0.0000

Data Index: 1299820 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 5.0089. Min Range: -5.0089

Max Act: 4.0360. Min Act: -0.0000

Data Index: 796366 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 5.0089. Min Range: -5.0089

Max Act: 3.4436. Min Act: -0.0000

Data Index: 746678 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 5.0089. Min Range: -5.0089

Max Act: 3.4111. Min Act: -0.0000

Data Index: 61383 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 5.0089. Min Range: -5.0089

Max Act: 3.3812. Min Act: -0.0000

Data Index: 4039 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 5.0089. Min Range: -5.0089

Max Act: 3.2644. Min Act: -0.0000

Data Index: 353214 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.9736. Min Act: -0.0000

Data Index: 1262341 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 5.0089. Min Range: -5.0089

Max Act: 3.1059. Min Act: -0.0000

Data Index: 10092 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.6387. Min Act: -0.0000

Data Index: 546131 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.7666. Min Act: -0.0000

Data Index: 1238354 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.6052. Min Act: -0.0000

Data Index: 578225 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.5840. Min Act: -0.0000

Data Index: 108140 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.4108. Min Act: -0.0000

Data Index: 258286 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.2311. Min Act: -0.0000

Data Index: 940876 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.1714. Min Act: -0.0000

Data Index: 162847 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.0367. Min Act: -0.0000

Data Index: 286853 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 5.0089. Min Range: -5.0089

Max Act: 2.1407. Min Act: -0.0000

Data Index: 875633 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 5.0089. Min Range: -5.0089

Max Act: 1.9865. Min Act: -0.0000

Data Index: 889109 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 5.0089. Min Range: -5.0089

Max Act: 1.9870. Min Act: -0.0000

Data Index: 1254087 (C4 (Web Text))

Max Activating Token Index: 405