Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 249 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.7471. Min Act: -0.1700

Data Index: 1263459 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.7471. Min Act: -0.1700

Data Index: 700960 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.6688. Min Act: -0.1700

Data Index: 1026252 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.6219. Min Act: -0.1700

Data Index: 522447 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.6219. Min Act: -0.1700

Data Index: 422935 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5906. Min Act: -0.1700

Data Index: 1305865 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.6062. Min Act: -0.1700

Data Index: 359493 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5749. Min Act: -0.1700

Data Index: 1195923 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5906. Min Act: -0.1700

Data Index: 1257180 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5749. Min Act: -0.1700

Data Index: 921784 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5593. Min Act: -0.1700

Data Index: 1344405 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5593. Min Act: -0.1700

Data Index: 170321 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5749. Min Act: -0.1700

Data Index: 1144126 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5436. Min Act: -0.1700

Data Index: 77301 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5436. Min Act: -0.1700

Data Index: 1288567 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5593. Min Act: -0.1700

Data Index: 1136516 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5593. Min Act: -0.1700

Data Index: 531362 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5436. Min Act: -0.1700

Data Index: 62974 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5279. Min Act: -0.1700

Data Index: 82263 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 3.7471. Min Range: -3.7471

Max Act: 3.5436. Min Act: -0.1700

Data Index: 1263428 (C4 (Web Text))

Max Activating Token Index: 735