Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 708 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.5641. Min Act: -0.1700

Data Index: 50543 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4701. Min Act: -0.1700

Data Index: 424072 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4701. Min Act: -0.1700

Data Index: 875814 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.4701. Min Act: -0.1700

Data Index: 1274006 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3761. Min Act: -0.1700

Data Index: 183430 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3917. Min Act: -0.1700

Data Index: 163268 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3604. Min Act: -0.1700

Data Index: 947665 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3604. Min Act: -0.1700

Data Index: 348439 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3604. Min Act: -0.1700

Data Index: 249621 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3447. Min Act: -0.1700

Data Index: 963730 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3917. Min Act: -0.1700

Data Index: 287980 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3604. Min Act: -0.1700

Data Index: 103585 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3447. Min Act: -0.1700

Data Index: 334509 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3447. Min Act: -0.1700

Data Index: 488759 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2976. Min Act: -0.1700

Data Index: 1255502 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3290. Min Act: -0.1700

Data Index: 24391 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1064692 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2662. Min Act: -0.1700

Data Index: 70126 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1082844 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2662. Min Act: -0.1700

Data Index: 236388 (C4 (Web Text))

Max Activating Token Index: 477