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

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

Neuron 1057 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: 3.7936. Min Range: -3.7936

Max Act: 3.7936. Min Act: -0.1700

Data Index: 228301 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.6998. Min Act: -0.1700

Data Index: 481613 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4962. Min Act: -0.1700

Data Index: 1075236 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4962. Min Act: -0.1700

Data Index: 830873 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.5275. Min Act: -0.1700

Data Index: 741947 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4962. Min Act: -0.1700

Data Index: 467600 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4649. Min Act: -0.1700

Data Index: 681644 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4492. Min Act: -0.1700

Data Index: 895347 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4178. Min Act: -0.1700

Data Index: 963233 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4022. Min Act: -0.1700

Data Index: 1242653 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.3551. Min Act: -0.1700

Data Index: 443932 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4335. Min Act: -0.1700

Data Index: 1041070 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.3865. Min Act: -0.1700

Data Index: 561571 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4335. Min Act: -0.1700

Data Index: 390649 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4022. Min Act: -0.1700

Data Index: 1089617 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4492. Min Act: -0.1700

Data Index: 124376 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.3865. Min Act: -0.1700

Data Index: 1165770 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.3865. Min Act: -0.1700

Data Index: 347650 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.4022. Min Act: -0.1700

Data Index: 1357914 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 3.7936. Min Range: -3.7936

Max Act: 3.3551. Min Act: -0.1700

Data Index: 1285568 (C4 (Web Text))

Max Activating Token Index: 248