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

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

Neuron 808 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: 3.3329. Min Range: -3.3329

Max Act: 3.3329. Min Act: -0.1700

Data Index: 268939 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.3329. Min Act: -0.1700

Data Index: 986968 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.2072. Min Act: -0.1700

Data Index: 272389 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.1600. Min Act: -0.1700

Data Index: 506676 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.1443. Min Act: -0.1700

Data Index: 233501 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.1285. Min Act: -0.1700

Data Index: 1940 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0970. Min Act: -0.1700

Data Index: 647796 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0654. Min Act: -0.1700

Data Index: 1081393 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0812. Min Act: -0.1700

Data Index: 256822 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0654. Min Act: -0.1700

Data Index: 319478 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0496. Min Act: -0.1700

Data Index: 578027 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0496. Min Act: -0.1700

Data Index: 1206785 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0654. Min Act: -0.1700

Data Index: 878678 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0338. Min Act: -0.1700

Data Index: 1044075 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0338. Min Act: -0.1700

Data Index: 60064 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0496. Min Act: -0.1700

Data Index: 895719 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0496. Min Act: -0.1700

Data Index: 1151122 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0338. Min Act: -0.1700

Data Index: 292488 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0338. Min Act: -0.1700

Data Index: 868426 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 3.3329. Min Range: -3.3329

Max Act: 3.0496. Min Act: -0.1700

Data Index: 684243 (C4 (Web Text))

Max Activating Token Index: 744