Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1344 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.7092. Min Act: -0.1700

Data Index: 1094543 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.6466. Min Act: -0.1700

Data Index: 474749 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.6466. Min Act: -0.1700

Data Index: 540400 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.6466. Min Act: -0.1700

Data Index: 357964 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.6153. Min Act: -0.1700

Data Index: 197452 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.5840. Min Act: -0.1700

Data Index: 1337342 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.5214. Min Act: -0.1700

Data Index: 997180 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.5527. Min Act: -0.1700

Data Index: 1080037 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.5527. Min Act: -0.1700

Data Index: 976286 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.5214. Min Act: -0.1700

Data Index: 442767 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.4900. Min Act: -0.1700

Data Index: 603468 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.5214. Min Act: -0.1700

Data Index: 194601 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.4900. Min Act: -0.1700

Data Index: 122129 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.5214. Min Act: -0.1700

Data Index: 26373 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.5527. Min Act: -0.1700

Data Index: 191361 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.5214. Min Act: -0.1700

Data Index: 546028 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.4900. Min Act: -0.1700

Data Index: 823938 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.4900. Min Act: -0.1700

Data Index: 821812 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.4900. Min Act: -0.1700

Data Index: 839794 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 3.7092. Min Range: -3.7092

Max Act: 3.4900. Min Act: -0.1700

Data Index: 819578 (C4 (Web Text))

Max Activating Token Index: 726