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

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

Neuron 477 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.4897. Min Act: -0.1700

Data Index: 329747 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.4584. Min Act: -0.1700

Data Index: 374931 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.4270. Min Act: -0.1700

Data Index: 519070 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.4113. Min Act: -0.1700

Data Index: 202518 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3957. Min Act: -0.1700

Data Index: 1341385 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3800. Min Act: -0.1700

Data Index: 211352 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3643. Min Act: -0.1700

Data Index: 289428 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3329. Min Act: -0.1700

Data Index: 507697 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3486. Min Act: -0.1700

Data Index: 380501 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3486. Min Act: -0.1700

Data Index: 916141 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3486. Min Act: -0.1700

Data Index: 771352 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3329. Min Act: -0.1700

Data Index: 317521 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3329. Min Act: -0.1700

Data Index: 426655 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3172. Min Act: -0.1700

Data Index: 31562 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3172. Min Act: -0.1700

Data Index: 884674 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3015. Min Act: -0.1700

Data Index: 194690 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3172. Min Act: -0.1700

Data Index: 1041580 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3172. Min Act: -0.1700

Data Index: 1133143 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3172. Min Act: -0.1700

Data Index: 1255322 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 3.4897. Min Range: -3.4897

Max Act: 3.3172. Min Act: -0.1700

Data Index: 442376 (C4 (Web Text))

Max Activating Token Index: 898