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

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

Neuron 1588 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7853. Min Act: -0.1700

Data Index: 78559 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7540. Min Act: -0.1700

Data Index: 507342 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7853. Min Act: -0.1700

Data Index: 195211 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7853. Min Act: -0.1700

Data Index: 256003 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7383. Min Act: -0.1700

Data Index: 980426 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7540. Min Act: -0.1700

Data Index: 69479 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7383. Min Act: -0.1700

Data Index: 675398 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7383. Min Act: -0.1700

Data Index: 1232354 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7383. Min Act: -0.1700

Data Index: 1273484 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7383. Min Act: -0.1700

Data Index: 695921 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7070. Min Act: -0.1700

Data Index: 668376 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.6914. Min Act: -0.1700

Data Index: 227490 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.7227. Min Act: -0.1700

Data Index: 70637 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.6914. Min Act: -0.1700

Data Index: 696115 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.6601. Min Act: -0.1700

Data Index: 1319332 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.6914. Min Act: -0.1700

Data Index: 193419 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1178459 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.6914. Min Act: -0.1700

Data Index: 398926 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.6914. Min Act: -0.1700

Data Index: 268192 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 3.7853. Min Range: -3.7853

Max Act: 3.6757. Min Act: -0.1700

Data Index: 1201255 (C4 (Web Text))

Max Activating Token Index: 178