Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 31 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.7823. Min Act: -0.1700

Data Index: 616279 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.6728. Min Act: -0.1700

Data Index: 738048 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.7041. Min Act: -0.1700

Data Index: 466881 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.6728. Min Act: -0.1700

Data Index: 1188500 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.6728. Min Act: -0.1700

Data Index: 546228 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.6258. Min Act: -0.1700

Data Index: 1099178 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.6102. Min Act: -0.1700

Data Index: 1302010 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5945. Min Act: -0.1700

Data Index: 949529 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.6415. Min Act: -0.1700

Data Index: 1022741 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5945. Min Act: -0.1700

Data Index: 420057 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.6102. Min Act: -0.1700

Data Index: 998542 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5632. Min Act: -0.1700

Data Index: 87716 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.6102. Min Act: -0.1700

Data Index: 1281379 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5789. Min Act: -0.1700

Data Index: 853369 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5789. Min Act: -0.1700

Data Index: 106141 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5789. Min Act: -0.1700

Data Index: 791099 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5632. Min Act: -0.1700

Data Index: 1328299 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5789. Min Act: -0.1700

Data Index: 765653 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5789. Min Act: -0.1700

Data Index: 1224403 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 3.7823. Min Range: -3.7823

Max Act: 3.5319. Min Act: -0.1700

Data Index: 1259046 (C4 (Web Text))

Max Activating Token Index: 626