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

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

Neuron 812 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.4805. Min Act: -0.1700

Data Index: 143946 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.4180. Min Act: -0.1700

Data Index: 543016 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.3867. Min Act: -0.1700

Data Index: 545893 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.4180. Min Act: -0.1700

Data Index: 1325124 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.3867. Min Act: -0.1700

Data Index: 1173016 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.3242. Min Act: -0.1700

Data Index: 564056 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.3555. Min Act: -0.1700

Data Index: 724084 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.4180. Min Act: -0.1700

Data Index: 273028 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2930. Min Act: -0.1700

Data Index: 1207824 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2930. Min Act: -0.1700

Data Index: 30364 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.3242. Min Act: -0.1700

Data Index: 417565 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2617. Min Act: -0.1700

Data Index: 625889 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2617. Min Act: -0.1700

Data Index: 260994 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2305. Min Act: -0.1700

Data Index: 456869 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2617. Min Act: -0.1700

Data Index: 263807 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2305. Min Act: -0.1700

Data Index: 696946 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2305. Min Act: -0.1700

Data Index: 1269023 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.1992. Min Act: -0.1700

Data Index: 128512 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2305. Min Act: -0.1699

Data Index: 92902 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 5.4805. Min Range: -5.4805

Max Act: 5.2617. Min Act: -0.1700

Data Index: 512684 (C4 (Web Text))

Max Activating Token Index: 818