Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1395 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.5439. Min Act: -0.1700

Data Index: 857128 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4656. Min Act: -0.1700

Data Index: 892970 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4342. Min Act: -0.1700

Data Index: 755125 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4342. Min Act: -0.1700

Data Index: 607655 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4185. Min Act: -0.1700

Data Index: 1270171 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4185. Min Act: -0.1700

Data Index: 280433 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4185. Min Act: -0.1700

Data Index: 497920 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4185. Min Act: -0.1700

Data Index: 986509 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 1285629 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4028. Min Act: -0.1700

Data Index: 368010 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4028. Min Act: -0.1700

Data Index: 727080 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4028. Min Act: -0.1700

Data Index: 1154776 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 698688 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 1169108 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 1192412 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 960018 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4028. Min Act: -0.1700

Data Index: 503055 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 678612 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 670274 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3715. Min Act: -0.1700

Data Index: 772910 (C4 (Web Text))

Max Activating Token Index: 387