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

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

Neuron 194 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: 3.5174. Min Range: -3.5174

Max Act: 3.5174. Min Act: -0.1700

Data Index: 311838 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.4391. Min Act: -0.1700

Data Index: 879922 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3763. Min Act: -0.1700

Data Index: 242111 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3449. Min Act: -0.1700

Data Index: 1157678 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3449. Min Act: -0.1700

Data Index: 391867 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3292. Min Act: -0.1700

Data Index: 32476 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.3292. Min Act: -0.1700

Data Index: 431112 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2664. Min Act: -0.1700

Data Index: 563572 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2507. Min Act: -0.1700

Data Index: 998853 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2035. Min Act: -0.1700

Data Index: 245032 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2035. Min Act: -0.1700

Data Index: 641434 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2035. Min Act: -0.1700

Data Index: 1133675 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2035. Min Act: -0.1700

Data Index: 28501 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.1878. Min Act: -0.1700

Data Index: 410247 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2035. Min Act: -0.1700

Data Index: 362919 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2035. Min Act: -0.1700

Data Index: 1056136 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2035. Min Act: -0.1700

Data Index: 432121 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.1878. Min Act: -0.1700

Data Index: 958162 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.1721. Min Act: -0.1700

Data Index: 985575 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.1721. Min Act: -0.1700

Data Index: 796651 (C4 (Web Text))

Max Activating Token Index: 160