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

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

Neuron 339 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: 2.9095. Min Range: -2.9095

Max Act: 2.9095. Min Act: -0.1700

Data Index: 1602077 (Python Code)

Max Activating Token Index: 909

Text #1

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.8199. Min Act: -0.1700

Data Index: 1363184 (Python Code)

Max Activating Token Index: 624

Text #2

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.7565. Min Act: -0.1700

Data Index: 112107 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.7526. Min Act: -0.1700

Data Index: 1519243 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.7215. Min Act: -0.1700

Data Index: 442508 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.7095. Min Act: -0.1700

Data Index: 1444500 (Python Code)

Max Activating Token Index: 146

Text #6

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.7072. Min Act: -0.1700

Data Index: 1455873 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.7105. Min Act: -0.1700

Data Index: 1105900 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.7154. Min Act: -0.1700

Data Index: 227416 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6875. Min Act: -0.1700

Data Index: 1494227 (Python Code)

Max Activating Token Index: 734

Text #10

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6852. Min Act: -0.1700

Data Index: 581251 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6932. Min Act: -0.1700

Data Index: 354125 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6700. Min Act: -0.1700

Data Index: 54504 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6628. Min Act: -0.1700

Data Index: 1525002 (Python Code)

Max Activating Token Index: 165

Text #14

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6616. Min Act: -0.1700

Data Index: 927116 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6885. Min Act: -0.1700

Data Index: 754573 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6646. Min Act: -0.1700

Data Index: 436114 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6494. Min Act: -0.1700

Data Index: 739026 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6530. Min Act: -0.1700

Data Index: 787318 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 2.9095. Min Range: -2.9095

Max Act: 2.6341. Min Act: -0.1700

Data Index: 938049 (C4 (Web Text))

Max Activating Token Index: 61