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

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

Neuron 1390 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.3119. Min Act: -0.1700

Data Index: 116557 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.3431. Min Act: -0.1700

Data Index: 692990 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.2494. Min Act: -0.1700

Data Index: 772260 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.2181. Min Act: -0.1700

Data Index: 848670 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1869. Min Act: -0.1700

Data Index: 748055 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1869. Min Act: -0.1700

Data Index: 212257 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.2181. Min Act: -0.1700

Data Index: 1058526 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.2806. Min Act: -0.1700

Data Index: 898430 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1556. Min Act: -0.1700

Data Index: 1268717 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1244. Min Act: -0.1700

Data Index: 645471 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1869. Min Act: -0.1700

Data Index: 149002 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.0931. Min Act: -0.1700

Data Index: 1199421 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.2494. Min Act: -0.1700

Data Index: 1216529 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1244. Min Act: -0.1700

Data Index: 1006656 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1244. Min Act: -0.1700

Data Index: 1226750 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1556. Min Act: -0.1700

Data Index: 403947 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.0931. Min Act: -0.1700

Data Index: 275737 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1556. Min Act: -0.1700

Data Index: 356750 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.1244. Min Act: -0.1700

Data Index: 34793 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 7.3431. Min Range: -7.3431

Max Act: 7.0931. Min Act: -0.1700

Data Index: 398773 (C4 (Web Text))

Max Activating Token Index: 161