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

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

Neuron 5076 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: 1.7384. Min Range: -1.7384

Max Act: 1.7384. Min Act: -0.0000

Data Index: 834646 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.5398. Min Act: -0.0000

Data Index: 1157371 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.4483. Min Act: -0.0000

Data Index: 78230 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.4381. Min Act: -0.0000

Data Index: 1221666 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3383. Min Act: -0.0000

Data Index: 352851 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.4239. Min Act: -0.0000

Data Index: 957899 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.4091. Min Act: -0.0000

Data Index: 941229 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.4138. Min Act: -0.0000

Data Index: 777676 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.4082. Min Act: -0.0000

Data Index: 1297834 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.4735. Min Act: -0.0000

Data Index: 295188 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3684. Min Act: -0.0000

Data Index: 284149 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3754. Min Act: -0.0000

Data Index: 136051 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1301303 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1007659 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3412. Min Act: -0.0000

Data Index: 499468 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3199. Min Act: -0.0000

Data Index: 1344930 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1128822 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3936. Min Act: -0.0000

Data Index: 418842 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.3154. Min Act: -0.0000

Data Index: 1207652 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 1.7384. Min Range: -1.7384

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1241361 (C4 (Web Text))

Max Activating Token Index: 267