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

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

Neuron 1131 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: 5.8893. Min Range: -5.8893

Max Act: 5.8893. Min Act: -0.1700

Data Index: 315238 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.5768. Min Act: -0.1700

Data Index: 289625 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.5455. Min Act: -0.1700

Data Index: 1350458 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.5455. Min Act: -0.1700

Data Index: 327840 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.4518. Min Act: -0.1700

Data Index: 773742 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.3268. Min Act: -0.1700

Data Index: 934926 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.4518. Min Act: -0.1700

Data Index: 429445 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.2955. Min Act: -0.1700

Data Index: 507690 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.2955. Min Act: -0.1700

Data Index: 850922 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.3268. Min Act: -0.1700

Data Index: 91635 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.3737. Min Act: -0.1700

Data Index: 506256 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.3424. Min Act: -0.1700

Data Index: 52696 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.3268. Min Act: -0.1700

Data Index: 866804 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.2799. Min Act: -0.1700

Data Index: 716035 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.3424. Min Act: -0.1700

Data Index: 5259 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.2487. Min Act: -0.1700

Data Index: 119182 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.2643. Min Act: -0.1700

Data Index: 373981 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.1705. Min Act: -0.1700

Data Index: 887822 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.2330. Min Act: -0.1699

Data Index: 1255933 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 5.8893. Min Range: -5.8893

Max Act: 5.1705. Min Act: -0.1700

Data Index: 557040 (C4 (Web Text))

Max Activating Token Index: 166