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

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

Neuron 908 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.9634. Min Act: -0.1700

Data Index: 799803 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.9009. Min Act: -0.1700

Data Index: 1046022 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.9009. Min Act: -0.1700

Data Index: 1230358 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8383. Min Act: -0.1700

Data Index: 487501 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8383. Min Act: -0.1700

Data Index: 656432 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8383. Min Act: -0.1700

Data Index: 384338 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8070. Min Act: -0.1700

Data Index: 144353 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.7758. Min Act: -0.1700

Data Index: 1040081 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8070. Min Act: -0.1700

Data Index: 1323815 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8070. Min Act: -0.1700

Data Index: 1357647 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8070. Min Act: -0.1700

Data Index: 852147 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8070. Min Act: -0.1700

Data Index: 252563 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8070. Min Act: -0.1700

Data Index: 385427 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.7758. Min Act: -0.1700

Data Index: 72485 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.7758. Min Act: -0.1700

Data Index: 586481 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.7758. Min Act: -0.1700

Data Index: 611515 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.7758. Min Act: -0.1700

Data Index: 181563 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.7758. Min Act: -0.1700

Data Index: 691226 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.8070. Min Act: -0.1700

Data Index: 755394 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 3.9634. Min Range: -3.9634

Max Act: 3.7758. Min Act: -0.1700

Data Index: 485534 (C4 (Web Text))

Max Activating Token Index: 453