Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1981 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.4202. Min Act: -0.1700

Data Index: 1089850 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.4202. Min Act: -0.1700

Data Index: 1432773 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.4202. Min Act: -0.1700

Data Index: 1576301 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.3261. Min Act: -0.1700

Data Index: 1999 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.3418. Min Act: -0.1700

Data Index: 1013836 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2633. Min Act: -0.1700

Data Index: 103598 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2633. Min Act: -0.1700

Data Index: 1418992 (Python Code)

Max Activating Token Index: 316

Text #7

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2790. Min Act: -0.1700

Data Index: 221747 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2790. Min Act: -0.1700

Data Index: 289123 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2633. Min Act: -0.1700

Data Index: 90635 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2633. Min Act: -0.1700

Data Index: 991476 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2318. Min Act: -0.1700

Data Index: 218320 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2318. Min Act: -0.1700

Data Index: 1344780 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2318. Min Act: -0.1700

Data Index: 95100 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2475. Min Act: -0.1700

Data Index: 1348864 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2475. Min Act: -0.1700

Data Index: 329789 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2475. Min Act: -0.1700

Data Index: 730185 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2318. Min Act: -0.1700

Data Index: 231153 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2161. Min Act: -0.1700

Data Index: 503362 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 3.4202. Min Range: -3.4202

Max Act: 3.2318. Min Act: -0.1700

Data Index: 627269 (C4 (Web Text))

Max Activating Token Index: 412