Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1400 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.8786. Min Act: -0.1700

Data Index: 550826 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.8161. Min Act: -0.1700

Data Index: 74352 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.7224. Min Act: -0.1700

Data Index: 82161 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6911. Min Act: -0.1700

Data Index: 718484 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6911. Min Act: -0.1700

Data Index: 217791 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6599. Min Act: -0.1700

Data Index: 641842 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.7224. Min Act: -0.1700

Data Index: 541378 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6911. Min Act: -0.1700

Data Index: 1245538 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6599. Min Act: -0.1700

Data Index: 1318692 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.5974. Min Act: -0.1700

Data Index: 486401 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6911. Min Act: -0.1700

Data Index: 1120230 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.7224. Min Act: -0.1700

Data Index: 794814 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6911. Min Act: -0.1700

Data Index: 1048750 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6599. Min Act: -0.1700

Data Index: 1055901 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6599. Min Act: -0.1700

Data Index: 712217 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6286. Min Act: -0.1700

Data Index: 293368 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.6286. Min Act: -0.1700

Data Index: 1107708 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.5036. Min Act: -0.1700

Data Index: 1184024 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.5349. Min Act: -0.1700

Data Index: 490731 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 7.8786. Min Range: -7.8786

Max Act: 7.5661. Min Act: -0.1700

Data Index: 1174533 (C4 (Web Text))

Max Activating Token Index: 814