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

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

Neuron 1566 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: 3.4596. Min Range: -3.4596

Max Act: 3.4596. Min Act: -0.1700

Data Index: 386204 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3812. Min Act: -0.1700

Data Index: 1125457 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3812. Min Act: -0.1699

Data Index: 1124045 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3499. Min Act: -0.1700

Data Index: 1326061 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3499. Min Act: -0.1700

Data Index: 550501 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3499. Min Act: -0.1700

Data Index: 464453 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3342. Min Act: -0.1700

Data Index: 174113 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3028. Min Act: -0.1700

Data Index: 298887 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3185. Min Act: -0.1700

Data Index: 846915 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.3028. Min Act: -0.1700

Data Index: 449671 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2870. Min Act: -0.1700

Data Index: 1229862 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2870. Min Act: -0.1700

Data Index: 909701 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2870. Min Act: -0.1700

Data Index: 1018083 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2556. Min Act: -0.1700

Data Index: 130583 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2713. Min Act: -0.1700

Data Index: 744910 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2713. Min Act: -0.1700

Data Index: 867279 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2713. Min Act: -0.1700

Data Index: 25669 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2399. Min Act: -0.1699

Data Index: 1342581 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2399. Min Act: -0.1700

Data Index: 775366 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 3.4596. Min Range: -3.4596

Max Act: 3.2242. Min Act: -0.1700

Data Index: 184130 (C4 (Web Text))

Max Activating Token Index: 880