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

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

Neuron 3961 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6367. Min Range: -4.6367

Max Act: 4.3447. Min Act: -0.0000

Data Index: 1310411 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 4.6367. Min Range: -4.6367

Max Act: 4.1089. Min Act: -0.0000

Data Index: 1150161 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 4.6367. Min Range: -4.6367

Max Act: 4.4430. Min Act: -0.0000

Data Index: 1273640 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 4.6367. Min Range: -4.6367

Max Act: 4.6367. Min Act: -0.0000

Data Index: 908558 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 4.6367. Min Range: -4.6367

Max Act: 3.4569. Min Act: -0.0000

Data Index: 464445 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 4.6367. Min Range: -4.6367

Max Act: 3.0566. Min Act: -0.0000

Data Index: 600644 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 4.6367. Min Range: -4.6367

Max Act: 3.0587. Min Act: -0.0000

Data Index: 299237 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.8842. Min Act: -0.0000

Data Index: 483760 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.8663. Min Act: -0.0000

Data Index: 272263 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.6417. Min Act: -0.0000

Data Index: 1187759 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.3610. Min Act: -0.0000

Data Index: 77593 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.1602. Min Act: -0.0000

Data Index: 663649 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.3045. Min Act: -0.0000

Data Index: 423377 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 4.6367. Min Range: -4.6367

Max Act: 1.9344. Min Act: -0.0000

Data Index: 323765 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.1315. Min Act: -0.0000

Data Index: 40554 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.2072. Min Act: -0.0000

Data Index: 697004 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.2125. Min Act: -0.0000

Data Index: 955435 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.1613. Min Act: -0.0000

Data Index: 1124034 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 4.6367. Min Range: -4.6367

Max Act: 1.5415. Min Act: -0.0000

Data Index: 288060 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 4.6367. Min Range: -4.6367

Max Act: 2.0819. Min Act: -0.0000

Data Index: 1072389 (C4 (Web Text))

Max Activating Token Index: 49