Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1905 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.4356. Min Act: -0.1700

Data Index: 431589 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2787. Min Act: -0.1700

Data Index: 205485 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2944. Min Act: -0.1700

Data Index: 41648 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2315. Min Act: -0.1700

Data Index: 559877 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2158. Min Act: -0.1700

Data Index: 95005 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2315. Min Act: -0.1700

Data Index: 1036798 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2315. Min Act: -0.1700

Data Index: 419490 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2158. Min Act: -0.1700

Data Index: 447643 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2001. Min Act: -0.1700

Data Index: 867109 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2001. Min Act: -0.1700

Data Index: 1189347 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2001. Min Act: -0.1700

Data Index: 842791 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.2001. Min Act: -0.1700

Data Index: 1274208 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.1844. Min Act: -0.1700

Data Index: 908720 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.1844. Min Act: -0.1700

Data Index: 945440 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.1686. Min Act: -0.1700

Data Index: 720171 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.1844. Min Act: -0.1700

Data Index: 1348052 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.1844. Min Act: -0.1700

Data Index: 444871 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.1844. Min Act: -0.1700

Data Index: 705141 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.1844. Min Act: -0.1700

Data Index: 1000787 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 3.4356. Min Range: -3.4356

Max Act: 3.1529. Min Act: -0.1700

Data Index: 222981 (C4 (Web Text))

Max Activating Token Index: 108