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

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

Neuron 1558 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: 3.8369. Min Range: -3.8369

Max Act: 3.8369. Min Act: -0.1700

Data Index: 614190 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.8056. Min Act: -0.1700

Data Index: 1095762 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.7743. Min Act: -0.1700

Data Index: 319005 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.7430. Min Act: -0.1700

Data Index: 1008223 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.7430. Min Act: -0.1700

Data Index: 1314145 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.7743. Min Act: -0.1700

Data Index: 1082614 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.7117. Min Act: -0.1700

Data Index: 97724 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.7117. Min Act: -0.1700

Data Index: 1236801 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6804. Min Act: -0.1700

Data Index: 570693 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6804. Min Act: -0.1700

Data Index: 1207689 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6022. Min Act: -0.1700

Data Index: 993810 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6648. Min Act: -0.1700

Data Index: 1163894 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6335. Min Act: -0.1700

Data Index: 657583 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6335. Min Act: -0.1700

Data Index: 105550 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6178. Min Act: -0.1700

Data Index: 1304238 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.7117. Min Act: -0.1700

Data Index: 295942 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6335. Min Act: -0.1700

Data Index: 779769 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6335. Min Act: -0.1700

Data Index: 1118904 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6178. Min Act: -0.1700

Data Index: 1191923 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6491. Min Act: -0.1700

Data Index: 855153 (C4 (Web Text))

Max Activating Token Index: 931