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

Dataset: Open Web Text

Neuron 2042 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: 4.1162. Min Range: -4.1162

Max Act: 4.1162. Min Act: -0.1700

Data Index: 5922413 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 4.1162. Min Range: -4.1162

Max Act: 4.0724. Min Act: -0.1700

Data Index: 3100938 (Open Web Text)

Max Activating Token Index: 433

Text #2

Max Range: 4.1162. Min Range: -4.1162

Max Act: 4.0912. Min Act: -0.1700

Data Index: 5429591 (Open Web Text)

Max Activating Token Index: 447

Text #3

Max Range: 4.1162. Min Range: -4.1162

Max Act: 4.0735. Min Act: -0.1700

Data Index: 3782806 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 4.1162. Min Range: -4.1162

Max Act: 4.0636. Min Act: -0.1700

Data Index: 719116 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 4.1162. Min Range: -4.1162

Max Act: 4.0418. Min Act: -0.1700

Data Index: 5968275 (Open Web Text)

Max Activating Token Index: 837

Text #6

Max Range: 4.1162. Min Range: -4.1162

Max Act: 4.0092. Min Act: -0.1700

Data Index: 6966352 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9906. Min Act: -0.1700

Data Index: 1012628 (Open Web Text)

Max Activating Token Index: 61

Text #8

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9868. Min Act: -0.1700

Data Index: 5064508 (Open Web Text)

Max Activating Token Index: 842

Text #9

Max Range: 4.1162. Min Range: -4.1162

Max Act: 4.0119. Min Act: -0.1700

Data Index: 8422326 (Open Web Text)

Max Activating Token Index: 592

Text #10

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9696. Min Act: -0.1700

Data Index: 8105196 (Open Web Text)

Max Activating Token Index: 899

Text #11

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9781. Min Act: -0.1700

Data Index: 6680606 (Open Web Text)

Max Activating Token Index: 20

Text #12

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9875. Min Act: -0.1700

Data Index: 3290030 (Open Web Text)

Max Activating Token Index: 31

Text #13

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9970. Min Act: -0.1700

Data Index: 5617471 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9402. Min Act: -0.1700

Data Index: 4501968 (Open Web Text)

Max Activating Token Index: 111

Text #15

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9456. Min Act: -0.1700

Data Index: 4964003 (Open Web Text)

Max Activating Token Index: 808

Text #16

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9801. Min Act: -0.1700

Data Index: 2484664 (Open Web Text)

Max Activating Token Index: 791

Text #17

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9430. Min Act: -0.1700

Data Index: 5469486 (Open Web Text)

Max Activating Token Index: 40

Text #18

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9385. Min Act: -0.1700

Data Index: 2698087 (Open Web Text)

Max Activating Token Index: 972

Text #19

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9409. Min Act: -0.1700

Data Index: 2300174 (Open Web Text)

Max Activating Token Index: 36