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

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

Neuron 668 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.9308. Min Act: -0.1700

Data Index: 453306 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8995. Min Act: -0.1700

Data Index: 183198 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8995. Min Act: -0.1700

Data Index: 710204 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.9308. Min Act: -0.1700

Data Index: 1346262 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8369. Min Act: -0.1700

Data Index: 621737 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8995. Min Act: -0.1700

Data Index: 146475 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8369. Min Act: -0.1700

Data Index: 258678 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8369. Min Act: -0.1700

Data Index: 1271413 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8369. Min Act: -0.1700

Data Index: 756899 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8369. Min Act: -0.1700

Data Index: 143 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8369. Min Act: -0.1700

Data Index: 1097298 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8057. Min Act: -0.1700

Data Index: 1220703 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.7744. Min Act: -0.1700

Data Index: 193984 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.7744. Min Act: -0.1700

Data Index: 1060662 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.7744. Min Act: -0.1700

Data Index: 1024464 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8057. Min Act: -0.1700

Data Index: 1312782 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8057. Min Act: -0.1700

Data Index: 1186171 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8682. Min Act: -0.1700

Data Index: 1200392 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8369. Min Act: -0.1700

Data Index: 614537 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8369. Min Act: -0.1700

Data Index: 1270346 (C4 (Web Text))

Max Activating Token Index: 608