Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1992 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.8965. Min Act: -0.1700

Data Index: 730101 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.8026. Min Act: -0.1700

Data Index: 214049 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.7088. Min Act: -0.1700

Data Index: 269756 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.7088. Min Act: -0.1700

Data Index: 407363 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 1261363 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.7088. Min Act: -0.1700

Data Index: 867804 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.7088. Min Act: -0.1700

Data Index: 529743 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 522701 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 1171519 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 477011 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 1267778 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 10610 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 580243 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 619689 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 70545 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6775. Min Act: -0.1700

Data Index: 4847 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6462. Min Act: -0.1700

Data Index: 655027 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6462. Min Act: -0.1700

Data Index: 778230 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6462. Min Act: -0.1700

Data Index: 869335 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 3.8965. Min Range: -3.8965

Max Act: 3.6462. Min Act: -0.1700

Data Index: 269990 (C4 (Web Text))

Max Activating Token Index: 24