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

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

Neuron 1078 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.5202. Min Act: -0.1700

Data Index: 976924 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.5202. Min Act: -0.1700

Data Index: 1147836 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.3327. Min Act: -0.1700

Data Index: 656526 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.2390. Min Act: -0.1700

Data Index: 479463 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.2390. Min Act: -0.1700

Data Index: 1216856 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.2390. Min Act: -0.1700

Data Index: 1333662 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1765. Min Act: -0.1700

Data Index: 957730 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1765. Min Act: -0.1700

Data Index: 946511 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1765. Min Act: -0.1700

Data Index: 1007681 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1452. Min Act: -0.1700

Data Index: 1177832 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1765. Min Act: -0.1700

Data Index: 880942 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1140. Min Act: -0.1700

Data Index: 359464 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1140. Min Act: -0.1700

Data Index: 1255783 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1452. Min Act: -0.1700

Data Index: 1160767 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1452. Min Act: -0.1700

Data Index: 888509 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1140. Min Act: -0.1700

Data Index: 1102770 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1140. Min Act: -0.1700

Data Index: 890658 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.1140. Min Act: -0.1700

Data Index: 191465 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.0515. Min Act: -0.1700

Data Index: 520691 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 5.5202. Min Range: -5.5202

Max Act: 5.0827. Min Act: -0.1700

Data Index: 356941 (C4 (Web Text))

Max Activating Token Index: 762