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

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

Neuron 546 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1299. Min Range: -5.1299

Max Act: 5.1299. Min Act: -0.1700

Data Index: 979345 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 5.1299. Min Range: -5.1299

Max Act: 5.1299. Min Act: -0.1700

Data Index: 970994 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.9737. Min Act: -0.1700

Data Index: 59803 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 5.1299. Min Range: -5.1299

Max Act: 5.0049. Min Act: -0.1700

Data Index: 277407 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.9737. Min Act: -0.1700

Data Index: 397207 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.8487. Min Act: -0.1700

Data Index: 375152 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.8799. Min Act: -0.1700

Data Index: 50423 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.8799. Min Act: -0.1700

Data Index: 1060294 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.8487. Min Act: -0.1700

Data Index: 33762 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.8487. Min Act: -0.1700

Data Index: 1310278 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.8174. Min Act: -0.1700

Data Index: 1049974 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.7862. Min Act: -0.1700

Data Index: 894389 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.8174. Min Act: -0.1700

Data Index: 88992 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.7862. Min Act: -0.1700

Data Index: 917020 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.7862. Min Act: -0.1700

Data Index: 227802 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.7862. Min Act: -0.1700

Data Index: 702780 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.7549. Min Act: -0.1700

Data Index: 116443 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.7549. Min Act: -0.1700

Data Index: 919614 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.7862. Min Act: -0.1700

Data Index: 430236 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 5.1299. Min Range: -5.1299

Max Act: 4.7862. Min Act: -0.1700

Data Index: 25878 (C4 (Web Text))

Max Activating Token Index: 321