Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1406 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.3495. Min Act: -0.1700

Data Index: 1160815 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.3219. Min Act: -0.1700

Data Index: 757501 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.3055. Min Act: -0.1700

Data Index: 1098950 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2998. Min Act: -0.1700

Data Index: 307629 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2952. Min Act: -0.1700

Data Index: 513239 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2761. Min Act: -0.1700

Data Index: 694210 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2709. Min Act: -0.1700

Data Index: 896808 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2591. Min Act: -0.1700

Data Index: 1339668 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2513. Min Act: -0.1700

Data Index: 508970 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2399. Min Act: -0.1700

Data Index: 895628 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2267. Min Act: -0.1700

Data Index: 615004 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.1958. Min Act: -0.1700

Data Index: 952101 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2058. Min Act: -0.1700

Data Index: 408003 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.1706. Min Act: -0.1700

Data Index: 930140 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.1915. Min Act: -0.1700

Data Index: 302624 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.1936. Min Act: -0.1700

Data Index: 846169 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.1881. Min Act: -0.1700

Data Index: 375260 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.2012. Min Act: -0.1700

Data Index: 689020 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.1809. Min Act: -0.1700

Data Index: 1224716 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 3.3495. Min Range: -3.3495

Max Act: 3.1880. Min Act: -0.1700

Data Index: 694963 (C4 (Web Text))

Max Activating Token Index: 706