Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1095 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.5795. Min Act: -0.1700

Data Index: 563547 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.5149. Min Act: -0.1700

Data Index: 309126 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.4462. Min Act: -0.1700

Data Index: 1092464 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.2870. Min Act: -0.1700

Data Index: 1230716 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.2935. Min Act: -0.1699

Data Index: 1328998 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.2297. Min Act: -0.1697

Data Index: 329907 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.2189. Min Act: -0.1700

Data Index: 1601579 (Python Code)

Max Activating Token Index: 213

Text #7

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1833. Min Act: -0.1700

Data Index: 1442382 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.2098. Min Act: -0.1700

Data Index: 233614 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.2179. Min Act: -0.1700

Data Index: 1267331 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1772. Min Act: -0.1700

Data Index: 207023 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1834. Min Act: -0.1700

Data Index: 688519 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1734. Min Act: -0.1700

Data Index: 660371 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1571. Min Act: -0.1700

Data Index: 1216604 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1694. Min Act: -0.1700

Data Index: 1526155 (Python Code)

Max Activating Token Index: 814

Text #15

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1562. Min Act: -0.1700

Data Index: 715131 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1522. Min Act: -0.1700

Data Index: 769053 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1638. Min Act: -0.1699

Data Index: 1510936 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1442. Min Act: -0.1700

Data Index: 1456247 (Python Code)

Max Activating Token Index: 206

Text #19

Max Range: 3.5795. Min Range: -3.5795

Max Act: 3.1441. Min Act: -0.1700

Data Index: 493141 (C4 (Web Text))

Max Activating Token Index: 173