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

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

Neuron 1213 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: 4.3667. Min Range: -4.3667

Max Act: 4.3667. Min Act: -0.1700

Data Index: 1023877 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.2438. Min Act: -0.1700

Data Index: 308566 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.2619. Min Act: -0.1700

Data Index: 387072 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.2195. Min Act: -0.1700

Data Index: 185056 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.2192. Min Act: -0.1700

Data Index: 1095097 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1942. Min Act: -0.1700

Data Index: 1274034 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1585. Min Act: -0.1700

Data Index: 140135 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1561. Min Act: -0.1700

Data Index: 357124 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1816. Min Act: -0.1700

Data Index: 1317598 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1649. Min Act: -0.1700

Data Index: 359046 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1487. Min Act: -0.1700

Data Index: 239021 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1227. Min Act: -0.1700

Data Index: 679623 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1333. Min Act: -0.1700

Data Index: 869625 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1160. Min Act: -0.1700

Data Index: 281418 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1377. Min Act: -0.1700

Data Index: 161804 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1284. Min Act: -0.1700

Data Index: 535067 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1247. Min Act: -0.1700

Data Index: 1227585 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.1288. Min Act: -0.1700

Data Index: 1027318 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.0997. Min Act: -0.1700

Data Index: 97540 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 4.3667. Min Range: -4.3667

Max Act: 4.0777. Min Act: -0.1700

Data Index: 767313 (C4 (Web Text))

Max Activating Token Index: 707