Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1200 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2239. Min Act: -0.0003

Data Index: 358489 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2641. Min Act: -0.0003

Data Index: 740998 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1136. Min Act: -0.0003

Data Index: 481626 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2086. Min Act: -0.0003

Data Index: 715909 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7583. Min Act: -0.0003

Data Index: 1330484 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2261. Min Act: -0.0003

Data Index: 994332 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2403. Min Act: -0.0003

Data Index: 667798 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0310. Min Act: -0.0003

Data Index: 239028 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9596. Min Act: -0.0003

Data Index: 1151410 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8973. Min Act: -0.0003

Data Index: 1022646 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8742. Min Act: -0.0003

Data Index: 49459 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9975. Min Act: -0.0003

Data Index: 660717 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8574. Min Act: -0.0003

Data Index: 208193 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8613. Min Act: -0.0003

Data Index: 544239 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9641. Min Act: -0.0003

Data Index: 289538 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8766. Min Act: -0.0003

Data Index: 1194656 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.7012. Min Act: -0.0003

Data Index: 191741 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9207. Min Act: -0.0003

Data Index: 555171 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.8646. Min Act: -0.0003

Data Index: 725486 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.2641. Min Range: -1.2641

Max Act: 0.9123. Min Act: -0.0003

Data Index: 239778 (C4 (Web Text))

Max Activating Token Index: 830