Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1127 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1209. Min Range: -4.1209

Max Act: 4.1209. Min Act: -0.1700

Data Index: 1036524 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 4.1209. Min Range: -4.1209

Max Act: 4.0839. Min Act: -0.1700

Data Index: 840634 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 4.1209. Min Range: -4.1209

Max Act: 4.0620. Min Act: -0.1700

Data Index: 1110369 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 4.1209. Min Range: -4.1209

Max Act: 4.0587. Min Act: -0.1700

Data Index: 416305 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 4.1209. Min Range: -4.1209

Max Act: 4.0297. Min Act: -0.1700

Data Index: 1260539 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 4.1209. Min Range: -4.1209

Max Act: 4.0312. Min Act: -0.1700

Data Index: 1304274 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 4.1209. Min Range: -4.1209

Max Act: 4.0041. Min Act: -0.1700

Data Index: 1087002 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9762. Min Act: -0.1700

Data Index: 334161 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9921. Min Act: -0.1700

Data Index: 301187 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9750. Min Act: -0.1700

Data Index: 590165 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9593. Min Act: -0.1700

Data Index: 1107354 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9538. Min Act: -0.1700

Data Index: 152922 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9419. Min Act: -0.1700

Data Index: 1208355 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9513. Min Act: -0.1700

Data Index: 1051179 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9317. Min Act: -0.1700

Data Index: 962683 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9382. Min Act: -0.1700

Data Index: 536256 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9160. Min Act: -0.1700

Data Index: 917249 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9046. Min Act: -0.1700

Data Index: 239012 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9202. Min Act: -0.1700

Data Index: 39161 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 4.1209. Min Range: -4.1209

Max Act: 3.9140. Min Act: -0.1700

Data Index: 335151 (C4 (Web Text))

Max Activating Token Index: 300