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

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

Neuron 263 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: 5.3898. Min Range: -5.3898

Max Act: 5.3898. Min Act: -0.1700

Data Index: 1302224 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.3273. Min Act: -0.1700

Data Index: 228245 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.1711. Min Act: -0.1700

Data Index: 292778 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.2023. Min Act: -0.1700

Data Index: 615760 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.1711. Min Act: -0.1700

Data Index: 138638 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.0773. Min Act: -0.1700

Data Index: 265417 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.1398. Min Act: -0.1700

Data Index: 1223252 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.0461. Min Act: -0.1700

Data Index: 565545 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.0773. Min Act: -0.1700

Data Index: 53762 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 5.3898. Min Range: -5.3898

Max Act: 4.9836. Min Act: -0.1700

Data Index: 719664 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.0461. Min Act: -0.1700

Data Index: 965431 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.0148. Min Act: -0.1700

Data Index: 361430 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.0461. Min Act: -0.1700

Data Index: 642899 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.0148. Min Act: -0.1700

Data Index: 534137 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 5.3898. Min Range: -5.3898

Max Act: 4.9523. Min Act: -0.1700

Data Index: 662110 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.0461. Min Act: -0.1700

Data Index: 464070 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 5.3898. Min Range: -5.3898

Max Act: 5.0461. Min Act: -0.1700

Data Index: 945566 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 5.3898. Min Range: -5.3898

Max Act: 4.9836. Min Act: -0.1700

Data Index: 668597 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 5.3898. Min Range: -5.3898

Max Act: 4.9836. Min Act: -0.1700

Data Index: 350419 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 5.3898. Min Range: -5.3898

Max Act: 4.9523. Min Act: -0.1700

Data Index: 1124747 (C4 (Web Text))

Max Activating Token Index: 476