Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1235 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 6.2805. Min Range: -6.2805

Max Act: 6.2805. Min Act: -0.1694

Data Index: 496167 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 6.2805. Min Range: -6.2805

Max Act: 6.0749. Min Act: -0.1648

Data Index: 12689 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 6.2805. Min Range: -6.2805

Max Act: 6.0639. Min Act: -0.1699

Data Index: 103900 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 6.2805. Min Range: -6.2805

Max Act: 6.0704. Min Act: -0.1700

Data Index: 449956 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.9990. Min Act: -0.1700

Data Index: 354249 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.9573. Min Act: -0.1700

Data Index: 683422 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.8667. Min Act: -0.1517

Data Index: 810555 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.8946. Min Act: -0.0332

Data Index: 340162 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.8405. Min Act: -0.1700

Data Index: 506421 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.8310. Min Act: -0.1700

Data Index: 442373 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.8349. Min Act: -0.1696

Data Index: 635327 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.8135. Min Act: -0.1700

Data Index: 287473 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.8233. Min Act: -0.1699

Data Index: 1191971 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.7937. Min Act: -0.1698

Data Index: 67108 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.8050. Min Act: -0.1700

Data Index: 492078 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.8085. Min Act: -0.1700

Data Index: 824335 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.7905. Min Act: -0.1700

Data Index: 450536 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.7841. Min Act: -0.1700

Data Index: 803101 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.7419. Min Act: -0.1699

Data Index: 577311 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 6.2805. Min Range: -6.2805

Max Act: 5.7390. Min Act: -0.1700

Data Index: 277978 (C4 (Web Text))

Max Activating Token Index: 549