Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 395 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.3456. Min Act: -0.1700

Data Index: 1085415 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.3456. Min Act: -0.1700

Data Index: 1188843 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.3456. Min Act: -0.1700

Data Index: 465191 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.1893. Min Act: -0.1700

Data Index: 330896 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.2206. Min Act: -0.1700

Data Index: 1214804 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.1581. Min Act: -0.1700

Data Index: 901005 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.0956. Min Act: -0.1700

Data Index: 133317 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.1581. Min Act: -0.1700

Data Index: 990709 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.0956. Min Act: -0.1700

Data Index: 478687 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.1268. Min Act: -0.1700

Data Index: 652175 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.0643. Min Act: -0.1700

Data Index: 1187848 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.0643. Min Act: -0.1700

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 7.3456. Min Range: -7.3456

Max Act: 6.9393. Min Act: -0.1700

Data Index: 95227 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.0018. Min Act: -0.1700

Data Index: 1225139 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 7.3456. Min Range: -7.3456

Max Act: 6.9706. Min Act: -0.1700

Data Index: 15159 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.0956. Min Act: -0.1700

Data Index: 1137772 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.0018. Min Act: -0.1700

Data Index: 248247 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 7.3456. Min Range: -7.3456

Max Act: 7.1268. Min Act: -0.1700

Data Index: 699317 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 7.3456. Min Range: -7.3456

Max Act: 6.9393. Min Act: -0.1700

Data Index: 889070 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 7.3456. Min Range: -7.3456

Max Act: 6.9081. Min Act: -0.1700

Data Index: 708480 (C4 (Web Text))

Max Activating Token Index: 787