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

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

Neuron 348 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.7371. Min Act: -0.1700

Data Index: 558374 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.7527. Min Act: -0.1700

Data Index: 930315 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.6589. Min Act: -0.1700

Data Index: 647244 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5649. Min Act: -0.1700

Data Index: 1247820 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5649. Min Act: -0.1700

Data Index: 675966 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5806. Min Act: -0.1700

Data Index: 906237 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5493. Min Act: -0.1700

Data Index: 285581 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5179. Min Act: -0.1700

Data Index: 169397 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5179. Min Act: -0.1700

Data Index: 297036 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5493. Min Act: -0.1700

Data Index: 574313 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5336. Min Act: -0.1700

Data Index: 550991 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5179. Min Act: -0.1700

Data Index: 1053087 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5023. Min Act: -0.1700

Data Index: 1348979 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.4866. Min Act: -0.1700

Data Index: 134207 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5336. Min Act: -0.1700

Data Index: 1237267 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.5023. Min Act: -0.1700

Data Index: 1170518 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.4552. Min Act: -0.1700

Data Index: 365790 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.4866. Min Act: -0.1700

Data Index: 479444 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.4552. Min Act: -0.1700

Data Index: 1024861 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 3.7527. Min Range: -3.7527

Max Act: 3.4396. Min Act: -0.1700

Data Index: 1045367 (C4 (Web Text))

Max Activating Token Index: 914