Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1152 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6712. Min Act: -0.1700

Data Index: 658843 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6547. Min Act: -0.1700

Data Index: 1137919 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.6121. Min Act: -0.1700

Data Index: 305794 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.5368. Min Act: -0.1700

Data Index: 1271837 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.5057. Min Act: -0.1700

Data Index: 64369 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.5056. Min Act: -0.1700

Data Index: 1325360 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3965. Min Act: -0.1700

Data Index: 781426 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3721. Min Act: -0.1700

Data Index: 874464 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3888. Min Act: -0.1700

Data Index: 836922 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3810. Min Act: -0.1700

Data Index: 17387 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3477. Min Act: -0.1700

Data Index: 365898 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3763. Min Act: -0.1700

Data Index: 1035168 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3914. Min Act: -0.1700

Data Index: 1144996 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3761. Min Act: -0.1700

Data Index: 21554 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3593. Min Act: -0.1700

Data Index: 437293 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.4211. Min Act: -0.1700

Data Index: 63415 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3449. Min Act: -0.1700

Data Index: 115504 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3220. Min Act: -0.1700

Data Index: 756777 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3173. Min Act: -0.1700

Data Index: 558436 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 3.6712. Min Range: -3.6712

Max Act: 3.3086. Min Act: -0.1700

Data Index: 337062 (C4 (Web Text))

Max Activating Token Index: 721