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

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

Neuron 3943 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5547. Min Act: -0.0000

Data Index: 486617 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5369. Min Act: -0.0001

Data Index: 712314 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4820. Min Act: -0.0001

Data Index: 870178 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4929. Min Act: -0.0000

Data Index: 553321 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4569. Min Act: -0.0000

Data Index: 724611 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4291. Min Act: -0.0000

Data Index: 1254687 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1154045 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4542. Min Act: -0.0001

Data Index: 199326 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1197918 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1070147 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3864. Min Act: -0.0000

Data Index: 499140 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4199. Min Act: -0.0001

Data Index: 1314745 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4233. Min Act: -0.0000

Data Index: 856263 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3767. Min Act: -0.0000

Data Index: 528196 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1538074 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3978. Min Act: -0.0000

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1145453 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1055007 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3936. Min Act: -0.0000

Data Index: 727507 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1386686 (Python Code)

Max Activating Token Index: 144