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

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

Neuron 660 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1319. Min Range: -5.1319

Max Act: 5.1319. Min Act: -0.1700

Data Index: 1159699 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 5.1319. Min Range: -5.1319

Max Act: 5.0694. Min Act: -0.1700

Data Index: 1186667 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 5.1319. Min Range: -5.1319

Max Act: 5.0382. Min Act: -0.1700

Data Index: 1152960 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 5.1319. Min Range: -5.1319

Max Act: 5.0382. Min Act: -0.1700

Data Index: 1289891 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 5.1319. Min Range: -5.1319

Max Act: 5.0382. Min Act: -0.1700

Data Index: 26119 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.8194. Min Act: -0.1700

Data Index: 503190 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.9757. Min Act: -0.1700

Data Index: 1304179 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.7569. Min Act: -0.1700

Data Index: 437358 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.7569. Min Act: -0.1700

Data Index: 677983 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.8507. Min Act: -0.1700

Data Index: 318396 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.8194. Min Act: -0.1700

Data Index: 166290 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.7882. Min Act: -0.1700

Data Index: 571847 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.7569. Min Act: -0.1700

Data Index: 305514 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.6944. Min Act: -0.1700

Data Index: 1057926 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.5694. Min Act: -0.1700

Data Index: 953802 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.6632. Min Act: -0.1700

Data Index: 1005346 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.6632. Min Act: -0.1700

Data Index: 1129183 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.6632. Min Act: -0.1700

Data Index: 217811 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.6632. Min Act: -0.1700

Data Index: 1592590 (Python Code)

Max Activating Token Index: 420

Text #19

Max Range: 5.1319. Min Range: -5.1319

Max Act: 4.7257. Min Act: -0.1700

Data Index: 791435 (C4 (Web Text))

Max Activating Token Index: 123