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

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

Neuron 1180 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: 3.4466. Min Range: -3.4466

Max Act: 3.4083. Min Act: -0.1700

Data Index: 1324370 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.4269. Min Act: -0.1700

Data Index: 764497 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.4466. Min Act: -0.1700

Data Index: 1150579 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3636. Min Act: -0.1700

Data Index: 276835 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3458. Min Act: -0.1700

Data Index: 273982 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3163. Min Act: -0.1700

Data Index: 301473 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3304. Min Act: -0.1700

Data Index: 828739 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3093. Min Act: -0.1700

Data Index: 1071651 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3273. Min Act: -0.1700

Data Index: 251878 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3130. Min Act: -0.1700

Data Index: 1099986 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3263. Min Act: -0.1700

Data Index: 295280 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3107. Min Act: -0.1700

Data Index: 470583 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3171. Min Act: -0.1700

Data Index: 538946 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3195. Min Act: -0.1700

Data Index: 1146531 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3247. Min Act: -0.1700

Data Index: 128813 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3386. Min Act: -0.1700

Data Index: 189140 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3288. Min Act: -0.1700

Data Index: 383106 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3112. Min Act: -0.1700

Data Index: 834749 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.3074. Min Act: -0.1700

Data Index: 168477 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 3.4466. Min Range: -3.4466

Max Act: 3.2684. Min Act: -0.1700

Data Index: 399309 (C4 (Web Text))

Max Activating Token Index: 485