Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1598 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.1620. Min Act: -0.1700

Data Index: 5700196 (Open Web Text)

Max Activating Token Index: 106

Text #1

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0714. Min Act: -0.1700

Data Index: 8201174 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0922. Min Act: -0.1700

Data Index: 5288378 (Open Web Text)

Max Activating Token Index: 553

Text #3

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0396. Min Act: -0.1700

Data Index: 1844870 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0397. Min Act: -0.1700

Data Index: 1029652 (Open Web Text)

Max Activating Token Index: 494

Text #5

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0482. Min Act: -0.1700

Data Index: 4492733 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0377. Min Act: -0.1700

Data Index: 4492731 (Open Web Text)

Max Activating Token Index: 242

Text #7

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0252. Min Act: -0.1700

Data Index: 1688831 (Open Web Text)

Max Activating Token Index: 460

Text #8

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0185. Min Act: -0.1700

Data Index: 4428712 (Open Web Text)

Max Activating Token Index: 482

Text #9

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0165. Min Act: -0.1700

Data Index: 184528 (Open Web Text)

Max Activating Token Index: 276

Text #10

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0085. Min Act: -0.1700

Data Index: 4528803 (Open Web Text)

Max Activating Token Index: 126

Text #11

Max Range: 4.1620. Min Range: -4.1620

Max Act: 3.9942. Min Act: -0.1700

Data Index: 6008889 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 4.1620. Min Range: -4.1620

Max Act: 4.0136. Min Act: -0.1700

Data Index: 122023 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 4.1620. Min Range: -4.1620

Max Act: 3.9861. Min Act: -0.1700

Data Index: 4813207 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 4.1620. Min Range: -4.1620

Max Act: 3.9767. Min Act: -0.1700

Data Index: 6261181 (Open Web Text)

Max Activating Token Index: 893

Text #15

Max Range: 4.1620. Min Range: -4.1620

Max Act: 3.9799. Min Act: -0.1700

Data Index: 3795130 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 4.1620. Min Range: -4.1620

Max Act: 3.9784. Min Act: -0.1700

Data Index: 5001029 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 4.1620. Min Range: -4.1620

Max Act: 3.9743. Min Act: -0.1700

Data Index: 356326 (Open Web Text)

Max Activating Token Index: 461

Text #18

Max Range: 4.1620. Min Range: -4.1620

Max Act: 3.9712. Min Act: -0.1700

Data Index: 2927648 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 4.1620. Min Range: -4.1620

Max Act: 3.9793. Min Act: -0.1700

Data Index: 683079 (Open Web Text)

Max Activating Token Index: 139