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

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

Neuron 1913 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: 7.2890. Min Range: -7.2890

Max Act: 7.1640. Min Act: -0.1700

Data Index: 1254784 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 7.2890. Min Range: -7.2890

Max Act: 7.1015. Min Act: -0.1700

Data Index: 1158736 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 7.2890. Min Range: -7.2890

Max Act: 7.0390. Min Act: -0.1700

Data Index: 130604 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 7.2890. Min Range: -7.2890

Max Act: 7.2890. Min Act: -0.1700

Data Index: 14409 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 7.2890. Min Range: -7.2890

Max Act: 7.1015. Min Act: -0.1700

Data Index: 1336292 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.9140. Min Act: -0.1700

Data Index: 497934 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.7890. Min Act: -0.1700

Data Index: 921736 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.8515. Min Act: -0.1700

Data Index: 996613 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.9140. Min Act: -0.1700

Data Index: 824592 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.9140. Min Act: -0.1700

Data Index: 1291623 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.8515. Min Act: -0.1700

Data Index: 484304 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.7890. Min Act: -0.1700

Data Index: 769941 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.7265. Min Act: -0.1700

Data Index: 1335341 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.7890. Min Act: -0.1700

Data Index: 854747 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.8515. Min Act: -0.1700

Data Index: 429266 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.9140. Min Act: -0.1700

Data Index: 491589 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.7265. Min Act: -0.1700

Data Index: 733335 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.8515. Min Act: -0.1700

Data Index: 929380 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.7265. Min Act: -0.1700

Data Index: 860988 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 7.2890. Min Range: -7.2890

Max Act: 6.7890. Min Act: -0.1700

Data Index: 119753 (C4 (Web Text))

Max Activating Token Index: 137