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

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

Neuron 386 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: 3.3172. Min Range: -3.3172

Max Act: 3.3172. Min Act: -0.1700

Data Index: 618599 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.3064. Min Act: -0.1700

Data Index: 81229 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2868. Min Act: -0.1700

Data Index: 1257110 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2763. Min Act: -0.1700

Data Index: 1339986 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2589. Min Act: -0.1700

Data Index: 1315153 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2736. Min Act: -0.1700

Data Index: 646025 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2775. Min Act: -0.1700

Data Index: 414264 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2567. Min Act: -0.1700

Data Index: 893983 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2618. Min Act: -0.1700

Data Index: 423998 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2483. Min Act: -0.1700

Data Index: 398426 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2578. Min Act: -0.1700

Data Index: 379807 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2275. Min Act: -0.1700

Data Index: 1280206 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2268. Min Act: -0.1699

Data Index: 1323688 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2056. Min Act: -0.1700

Data Index: 961653 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2146. Min Act: -0.1700

Data Index: 659736 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.2068. Min Act: -0.1700

Data Index: 397141 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.1976. Min Act: -0.1700

Data Index: 256854 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.1970. Min Act: -0.1700

Data Index: 1233097 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.1890. Min Act: -0.1700

Data Index: 1158499 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 3.3172. Min Range: -3.3172

Max Act: 3.1888. Min Act: -0.1700

Data Index: 750873 (C4 (Web Text))

Max Activating Token Index: 485