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

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

Neuron 928 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.8844. Min Act: -0.1700

Data Index: 401507 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.8219. Min Act: -0.1700

Data Index: 2822 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7280. Min Act: -0.1700

Data Index: 10981 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.8219. Min Act: -0.1700

Data Index: 880485 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7280. Min Act: -0.1700

Data Index: 888018 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7280. Min Act: -0.1700

Data Index: 625862 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7593. Min Act: -0.1700

Data Index: 553040 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7280. Min Act: -0.1700

Data Index: 1177399 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7280. Min Act: -0.1700

Data Index: 488358 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.6967. Min Act: -0.1700

Data Index: 1221019 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.6967. Min Act: -0.1700

Data Index: 769172 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.6967. Min Act: -0.1700

Data Index: 987305 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7906. Min Act: -0.1700

Data Index: 396536 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.6654. Min Act: -0.1700

Data Index: 835500 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7280. Min Act: -0.1700

Data Index: 944023 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7593. Min Act: -0.1700

Data Index: 245818 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.6967. Min Act: -0.1700

Data Index: 192372 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.6654. Min Act: -0.1700

Data Index: 1337373 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.7280. Min Act: -0.1700

Data Index: 18227 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 3.8844. Min Range: -3.8844

Max Act: 3.5715. Min Act: -0.1700

Data Index: 309370 (C4 (Web Text))

Max Activating Token Index: 686