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

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

Neuron 677 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: 4.0199. Min Range: -4.0199

Max Act: 4.0199. Min Act: -0.1700

Data Index: 1052027 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8378. Min Act: -0.1700

Data Index: 748923 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8434. Min Act: -0.1700

Data Index: 367600 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8381. Min Act: -0.1700

Data Index: 978705 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8484. Min Act: -0.1700

Data Index: 587363 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8213. Min Act: -0.1700

Data Index: 138622 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8359. Min Act: -0.1700

Data Index: 1240201 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8309. Min Act: -0.1700

Data Index: 275537 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8488. Min Act: -0.1700

Data Index: 836568 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8035. Min Act: -0.1700

Data Index: 117354 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8325. Min Act: -0.1700

Data Index: 1214094 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7884. Min Act: -0.1700

Data Index: 1110173 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7761. Min Act: -0.1700

Data Index: 1191051 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7711. Min Act: -0.1700

Data Index: 311357 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7885. Min Act: -0.1700

Data Index: 1184411 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.8008. Min Act: -0.1700

Data Index: 1253789 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7547. Min Act: -0.1700

Data Index: 1142736 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7576. Min Act: -0.1700

Data Index: 109204 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7657. Min Act: -0.1700

Data Index: 1228507 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 4.0199. Min Range: -4.0199

Max Act: 3.7587. Min Act: -0.1700

Data Index: 1237507 (C4 (Web Text))

Max Activating Token Index: 306