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

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

Neuron 1698 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.7556. Min Act: -0.1700

Data Index: 318335 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.6930. Min Act: -0.1700

Data Index: 943335 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.5678. Min Act: -0.1700

Data Index: 463065 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.5521. Min Act: -0.1700

Data Index: 1082847 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.5365. Min Act: -0.1700

Data Index: 233757 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.5208. Min Act: -0.1700

Data Index: 1176178 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.3169. Min Act: -0.1700

Data Index: 331954 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.2698. Min Act: -0.1700

Data Index: 127989 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.2698. Min Act: -0.1700

Data Index: 1621143 (Python Code)

Max Activating Token Index: 817

Text #9

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.2541. Min Act: -0.1700

Data Index: 1020174 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.2384. Min Act: -0.1700

Data Index: 1311634 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.2226. Min Act: -0.1700

Data Index: 140115 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1263394 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.1439. Min Act: -0.1700

Data Index: 465602 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1160985 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.1439. Min Act: -0.1700

Data Index: 1006121 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.1282. Min Act: -0.1700

Data Index: 111916 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.1282. Min Act: -0.1700

Data Index: 327520 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1158350 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.7556. Min Range: -3.7556

Max Act: 3.1282. Min Act: -0.1700

Data Index: 425814 (C4 (Web Text))

Max Activating Token Index: 464