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

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

Neuron 76 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: 3.9939. Min Range: -3.9939

Max Act: 3.9939. Min Act: -0.1700

Data Index: 1274443 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.7437. Min Act: -0.1700

Data Index: 1272720 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.8062. Min Act: -0.1700

Data Index: 831307 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.7280. Min Act: -0.1700

Data Index: 939423 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.7437. Min Act: -0.1700

Data Index: 355493 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6967. Min Act: -0.1700

Data Index: 402978 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6654. Min Act: -0.1700

Data Index: 105970 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6654. Min Act: -0.1700

Data Index: 993547 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6967. Min Act: -0.1700

Data Index: 594264 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6498. Min Act: -0.1700

Data Index: 938015 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6498. Min Act: -0.1700

Data Index: 1349855 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6341. Min Act: -0.1700

Data Index: 145528 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6341. Min Act: -0.1700

Data Index: 713990 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6498. Min Act: -0.1700

Data Index: 253931 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6185. Min Act: -0.1700

Data Index: 486918 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.5871. Min Act: -0.1700

Data Index: 1075408 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6028. Min Act: -0.1700

Data Index: 459104 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.5715. Min Act: -0.1700

Data Index: 746575 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.6185. Min Act: -0.1700

Data Index: 762161 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 3.9939. Min Range: -3.9939

Max Act: 3.5871. Min Act: -0.1700

Data Index: 1059614 (C4 (Web Text))

Max Activating Token Index: 339