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

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

Neuron 2736 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.5884. Min Act: -0.0001

Data Index: 800262 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.4055. Min Act: -0.0001

Data Index: 175067 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.2193. Min Act: -0.0001

Data Index: 603406 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.2234. Min Act: -0.0000

Data Index: 319523 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.3616. Min Act: -0.0001

Data Index: 754052 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.5075. Min Act: -0.0001

Data Index: 633491 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.0234. Min Act: -0.0001

Data Index: 548117 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.1459. Min Act: -0.0001

Data Index: 428814 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.2492. Min Act: -0.0001

Data Index: 881502 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.2323. Min Act: -0.0001

Data Index: 596652 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 5.5884. Min Range: -5.5884

Max Act: 4.9942. Min Act: -0.0001

Data Index: 1294337 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 5.5884. Min Range: -5.5884

Max Act: 4.7436. Min Act: -0.0001

Data Index: 1281238 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.0694. Min Act: -0.0001

Data Index: 264316 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 5.5884. Min Range: -5.5884

Max Act: 4.8460. Min Act: -0.0001

Data Index: 533065 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 5.5884. Min Range: -5.5884

Max Act: 4.5494. Min Act: -0.0001

Data Index: 1109292 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.2192. Min Act: -0.0001

Data Index: 719049 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.2021. Min Act: -0.0001

Data Index: 240495 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.0466. Min Act: -0.0000

Data Index: 826181 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.0066. Min Act: -0.0001

Data Index: 230117 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 5.5884. Min Range: -5.5884

Max Act: 5.1982. Min Act: -0.0001

Data Index: 903417 (C4 (Web Text))

Max Activating Token Index: 486