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

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

Neuron 849 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: 3.1953. Min Range: -3.1953

Max Act: 3.1953. Min Act: -0.1700

Data Index: 231030 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.1481. Min Act: -0.1700

Data Index: 852462 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.1324. Min Act: -0.1700

Data Index: 300260 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.1008. Min Act: -0.1700

Data Index: 211151 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0851. Min Act: -0.1700

Data Index: 6462 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1477019 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0535. Min Act: -0.1700

Data Index: 660928 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0693. Min Act: -0.1700

Data Index: 1345567 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0377. Min Act: -0.1700

Data Index: 23201 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0535. Min Act: -0.1700

Data Index: 238745 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0377. Min Act: -0.1700

Data Index: 530086 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0219. Min Act: -0.1700

Data Index: 811690 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0535. Min Act: -0.1700

Data Index: 819222 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0219. Min Act: -0.1700

Data Index: 560890 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0219. Min Act: -0.1700

Data Index: 531524 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0061. Min Act: -0.1700

Data Index: 954481 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0061. Min Act: -0.1700

Data Index: 1139831 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 3.1953. Min Range: -3.1953

Max Act: 2.9903. Min Act: -0.1700

Data Index: 1041778 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0061. Min Act: -0.1700

Data Index: 47015 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 3.1953. Min Range: -3.1953

Max Act: 3.0061. Min Act: -0.1700

Data Index: 957262 (C4 (Web Text))

Max Activating Token Index: 467