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

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

Neuron 105 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: 3.8697. Min Range: -3.8697

Max Act: 3.8697. Min Act: -0.1700

Data Index: 427204 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.7132. Min Act: -0.1700

Data Index: 526439 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.6819. Min Act: -0.1700

Data Index: 560421 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.5567. Min Act: -0.1700

Data Index: 893629 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.5567. Min Act: -0.1700

Data Index: 1006080 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.5254. Min Act: -0.1700

Data Index: 429761 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4627. Min Act: -0.1700

Data Index: 483017 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4470. Min Act: -0.1700

Data Index: 1172740 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4784. Min Act: -0.1700

Data Index: 509679 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4940. Min Act: -0.1700

Data Index: 834052 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4313. Min Act: -0.1700

Data Index: 542571 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4313. Min Act: -0.1700

Data Index: 616561 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4157. Min Act: -0.1700

Data Index: 528303 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.3529. Min Act: -0.1700

Data Index: 942933 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4313. Min Act: -0.1700

Data Index: 930088 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4000. Min Act: -0.1700

Data Index: 1266733 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.3843. Min Act: -0.1700

Data Index: 6421 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4157. Min Act: -0.1700

Data Index: 797530 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.4157. Min Act: -0.1700

Data Index: 1142980 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 3.8697. Min Range: -3.8697

Max Act: 3.3372. Min Act: -0.1700

Data Index: 844593 (C4 (Web Text))

Max Activating Token Index: 540