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

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

Neuron 1230 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1646. Min Range: -3.1646

Max Act: 3.1646. Min Act: -0.1700

Data Index: 1151910 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 3.1646. Min Range: -3.1646

Max Act: 3.1016. Min Act: -0.1700

Data Index: 1272629 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 3.1646. Min Range: -3.1646

Max Act: 3.0700. Min Act: -0.1700

Data Index: 222273 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 3.1646. Min Range: -3.1646

Max Act: 3.0385. Min Act: -0.1700

Data Index: 72860 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 3.1646. Min Range: -3.1646

Max Act: 3.0069. Min Act: -0.1700

Data Index: 102592 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.9594. Min Act: -0.1700

Data Index: 415281 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.9436. Min Act: -0.1700

Data Index: 48983 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.9277. Min Act: -0.1700

Data Index: 420808 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.9277. Min Act: -0.1700

Data Index: 590248 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.9119. Min Act: -0.1700

Data Index: 687942 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.9119. Min Act: -0.1700

Data Index: 56434 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.8802. Min Act: -0.1700

Data Index: 422104 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.8484. Min Act: -0.1700

Data Index: 966995 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.8643. Min Act: -0.1700

Data Index: 1088932 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.8325. Min Act: -0.1700

Data Index: 845259 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.8484. Min Act: -0.1700

Data Index: 987107 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.8484. Min Act: -0.1700

Data Index: 868524 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.8484. Min Act: -0.1700

Data Index: 1185320 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.8325. Min Act: -0.1700

Data Index: 529417 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 3.1646. Min Range: -3.1646

Max Act: 2.8166. Min Act: -0.1700

Data Index: 707911 (C4 (Web Text))

Max Activating Token Index: 206