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

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

Neuron 1044 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: 3.8399. Min Range: -3.8399

Max Act: 3.8399. Min Act: -0.1700

Data Index: 1103108 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.7929. Min Act: -0.1700

Data Index: 127376 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.7419. Min Act: -0.1700

Data Index: 1270411 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.7124. Min Act: -0.1700

Data Index: 1139606 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.7161. Min Act: -0.1700

Data Index: 1221952 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1192191 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.7053. Min Act: -0.1700

Data Index: 1325542 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.7097. Min Act: -0.1700

Data Index: 485883 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.7065. Min Act: -0.1700

Data Index: 382167 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6860. Min Act: -0.1700

Data Index: 146114 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6819. Min Act: -0.1700

Data Index: 1086475 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6912. Min Act: -0.1700

Data Index: 1102118 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6810. Min Act: -0.1700

Data Index: 712823 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6848. Min Act: -0.1700

Data Index: 332376 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6473. Min Act: -0.1700

Data Index: 385770 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6719. Min Act: -0.1700

Data Index: 956151 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6601. Min Act: -0.1700

Data Index: 541056 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6660. Min Act: -0.1700

Data Index: 1402961 (Python Code)

Max Activating Token Index: 719

Text #18

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6559. Min Act: -0.1700

Data Index: 511849 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 3.8399. Min Range: -3.8399

Max Act: 3.6486. Min Act: -0.1700

Data Index: 1124960 (C4 (Web Text))

Max Activating Token Index: 195