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

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

Neuron 1996 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: 3.8393. Min Range: -3.8393

Max Act: 3.8393. Min Act: -0.1700

Data Index: 992884 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.8393. Min Act: -0.1700

Data Index: 801113 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.7141. Min Act: -0.1700

Data Index: 451862 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6672. Min Act: -0.1700

Data Index: 393878 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.6516. Min Act: -0.1700

Data Index: 958504 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5889. Min Act: -0.1700

Data Index: 227736 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5263. Min Act: -0.1700

Data Index: 329776 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5420. Min Act: -0.1700

Data Index: 884486 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5106. Min Act: -0.1700

Data Index: 961797 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5263. Min Act: -0.1700

Data Index: 309972 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5263. Min Act: -0.1700

Data Index: 485001 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5576. Min Act: -0.1700

Data Index: 861491 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.4793. Min Act: -0.1700

Data Index: 219560 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5106. Min Act: -0.1700

Data Index: 719821 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.4793. Min Act: -0.1700

Data Index: 833678 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5106. Min Act: -0.1700

Data Index: 599188 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5106. Min Act: -0.1700

Data Index: 440236 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.5106. Min Act: -0.1700

Data Index: 684346 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.4950. Min Act: -0.1700

Data Index: 1191880 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 3.8393. Min Range: -3.8393

Max Act: 3.4950. Min Act: -0.1700

Data Index: 1221260 (C4 (Web Text))

Max Activating Token Index: 420