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

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

Neuron 1736 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: 4.4950. Min Range: -4.4950

Max Act: 4.4950. Min Act: -0.1700

Data Index: 849509 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.3763. Min Act: -0.1700

Data Index: 368736 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.3188. Min Act: -0.1700

Data Index: 1604689 (Python Code)

Max Activating Token Index: 905

Text #3

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.3424. Min Act: -0.1700

Data Index: 1386931 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.2735. Min Act: -0.1700

Data Index: 869089 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.2625. Min Act: -0.1700

Data Index: 376734 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.2547. Min Act: -0.1700

Data Index: 1497142 (Python Code)

Max Activating Token Index: 539

Text #7

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.2616. Min Act: -0.1700

Data Index: 846413 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.2584. Min Act: -0.1700

Data Index: 531133 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.1849. Min Act: -0.1700

Data Index: 743565 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.2069. Min Act: -0.1700

Data Index: 95073 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.1722. Min Act: -0.1700

Data Index: 1181198 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.1699. Min Act: -0.1700

Data Index: 932659 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.1538. Min Act: -0.1700

Data Index: 1432242 (Python Code)

Max Activating Token Index: 804

Text #14

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.0904. Min Act: -0.1700

Data Index: 1283340 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.0948. Min Act: -0.1700

Data Index: 1510918 (Python Code)

Max Activating Token Index: 581

Text #16

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.1245. Min Act: -0.1700

Data Index: 1364882 (Python Code)

Max Activating Token Index: 423

Text #17

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.0532. Min Act: -0.1700

Data Index: 1187747 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.0856. Min Act: -0.1700

Data Index: 969264 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 4.4950. Min Range: -4.4950

Max Act: 4.0455. Min Act: -0.1700

Data Index: 556731 (C4 (Web Text))

Max Activating Token Index: 959