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

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

Neuron 1358 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: 3.6241. Min Range: -3.6241

Max Act: 3.6241. Min Act: -0.1700

Data Index: 392139 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.6241. Min Act: -0.1700

Data Index: 1177255 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.5927. Min Act: -0.1700

Data Index: 391636 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.5614. Min Act: -0.1700

Data Index: 1289106 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.5614. Min Act: -0.1700

Data Index: 1032390 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.5301. Min Act: -0.1700

Data Index: 1330854 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.5614. Min Act: -0.1700

Data Index: 214619 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4988. Min Act: -0.1700

Data Index: 202772 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4988. Min Act: -0.1700

Data Index: 897242 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.5614. Min Act: -0.1700

Data Index: 740565 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.5301. Min Act: -0.1700

Data Index: 1308694 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4988. Min Act: -0.1700

Data Index: 163110 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4988. Min Act: -0.1700

Data Index: 1335886 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4674. Min Act: -0.1700

Data Index: 968225 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4988. Min Act: -0.1700

Data Index: 760030 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4361. Min Act: -0.1700

Data Index: 785443 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4674. Min Act: -0.1700

Data Index: 875674 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4674. Min Act: -0.1700

Data Index: 258738 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4361. Min Act: -0.1700

Data Index: 1083004 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 3.6241. Min Range: -3.6241

Max Act: 3.4988. Min Act: -0.1700

Data Index: 1091139 (C4 (Web Text))

Max Activating Token Index: 779