Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 42 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1475. Min Range: -5.1475

Max Act: 5.1475. Min Act: -0.1700

Data Index: 481076 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 5.1475. Min Range: -5.1475

Max Act: 5.1475. Min Act: -0.1700

Data Index: 76531 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 5.1475. Min Range: -5.1475

Max Act: 5.1475. Min Act: -0.1700

Data Index: 844286 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 5.1475. Min Range: -5.1475

Max Act: 5.0850. Min Act: -0.1700

Data Index: 400272 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 5.1475. Min Range: -5.1475

Max Act: 5.0537. Min Act: -0.1700

Data Index: 334537 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 5.1475. Min Range: -5.1475

Max Act: 5.0850. Min Act: -0.1700

Data Index: 358394 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 5.1475. Min Range: -5.1475

Max Act: 5.0537. Min Act: -0.1700

Data Index: 1096635 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 5.1475. Min Range: -5.1475

Max Act: 5.0225. Min Act: -0.1700

Data Index: 1040493 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.8975. Min Act: -0.1700

Data Index: 1180347 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.8975. Min Act: -0.1700

Data Index: 1216611 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.8662. Min Act: -0.1700

Data Index: 739379 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.8975. Min Act: -0.1700

Data Index: 601559 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.8662. Min Act: -0.1700

Data Index: 46128 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.8037. Min Act: -0.1700

Data Index: 257630 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.7725. Min Act: -0.1700

Data Index: 525669 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.7412. Min Act: -0.1700

Data Index: 1136330 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.7412. Min Act: -0.1700

Data Index: 679912 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.7412. Min Act: -0.1700

Data Index: 2292 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.7100. Min Act: -0.1700

Data Index: 376424 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 5.1475. Min Range: -5.1475

Max Act: 4.7725. Min Act: -0.1700

Data Index: 1006177 (C4 (Web Text))

Max Activating Token Index: 723