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

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

Neuron 1337 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: 3.8936. Min Range: -3.8936

Max Act: 3.8936. Min Act: -0.1700

Data Index: 39900 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.8624. Min Act: -0.1700

Data Index: 885641 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.8311. Min Act: -0.1700

Data Index: 281164 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7998. Min Act: -0.1700

Data Index: 1181231 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7998. Min Act: -0.1700

Data Index: 1269749 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7998. Min Act: -0.1700

Data Index: 900685 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7529. Min Act: -0.1700

Data Index: 1345166 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7529. Min Act: -0.1700

Data Index: 1289681 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7529. Min Act: -0.1700

Data Index: 324194 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7216. Min Act: -0.1700

Data Index: 870723 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7372. Min Act: -0.1700

Data Index: 1087640 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7059. Min Act: -0.1700

Data Index: 133310 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7059. Min Act: -0.1700

Data Index: 158960 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.6903. Min Act: -0.1700

Data Index: 318399 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7372. Min Act: -0.1700

Data Index: 684878 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7059. Min Act: -0.1700

Data Index: 505791 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7216. Min Act: -0.1700

Data Index: 1068087 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7059. Min Act: -0.1700

Data Index: 919788 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.7216. Min Act: -0.1700

Data Index: 239585 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 3.8936. Min Range: -3.8936

Max Act: 3.6590. Min Act: -0.1700

Data Index: 856001 (C4 (Web Text))

Max Activating Token Index: 358