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

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

Neuron 930 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: 3.4677. Min Range: -3.4677

Max Act: 3.4677. Min Act: -0.1700

Data Index: 1004537 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.4050. Min Act: -0.1700

Data Index: 322956 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3893. Min Act: -0.1700

Data Index: 453083 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3737. Min Act: -0.1700

Data Index: 1087258 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3580. Min Act: -0.1700

Data Index: 1188157 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3580. Min Act: -0.1700

Data Index: 929683 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3423. Min Act: -0.1700

Data Index: 553476 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3423. Min Act: -0.1700

Data Index: 580760 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3266. Min Act: -0.1700

Data Index: 152902 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3266. Min Act: -0.1700

Data Index: 451952 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3266. Min Act: -0.1700

Data Index: 123513 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3109. Min Act: -0.1700

Data Index: 557049 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3109. Min Act: -0.1700

Data Index: 520020 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3266. Min Act: -0.1700

Data Index: 1116154 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3266. Min Act: -0.1700

Data Index: 834163 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.2952. Min Act: -0.1700

Data Index: 1497348 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3109. Min Act: -0.1700

Data Index: 884344 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.2952. Min Act: -0.1700

Data Index: 423380 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.3109. Min Act: -0.1700

Data Index: 590956 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 3.4677. Min Range: -3.4677

Max Act: 3.2952. Min Act: -0.1700

Data Index: 526646 (C4 (Web Text))

Max Activating Token Index: 560