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

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

Neuron 1040 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: 3.4716. Min Range: -3.4716

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1331342 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.4716. Min Act: -0.1700

Data Index: 381967 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.4402. Min Act: -0.1700

Data Index: 12920 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.3775. Min Act: -0.1700

Data Index: 946087 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.3461. Min Act: -0.1700

Data Index: 895224 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2833. Min Act: -0.1700

Data Index: 968506 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2518. Min Act: -0.1700

Data Index: 315231 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2204. Min Act: -0.1700

Data Index: 455250 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2204. Min Act: -0.1700

Data Index: 397758 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1115459 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1214011 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1889. Min Act: -0.1700

Data Index: 995451 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1260. Min Act: -0.1700

Data Index: 759549 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2204. Min Act: -0.1700

Data Index: 855103 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2204. Min Act: -0.1700

Data Index: 1151423 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1575. Min Act: -0.1700

Data Index: 1024853 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1575. Min Act: -0.1700

Data Index: 513372 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1575. Min Act: -0.1700

Data Index: 750268 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1260. Min Act: -0.1700

Data Index: 1168044 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.1575. Min Act: -0.1700

Data Index: 1027334 (C4 (Web Text))

Max Activating Token Index: 104