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

Dataset: Open Web Text

Neuron 1899 in Layer 2

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: 3.7104. Min Range: -3.7104

Max Act: 3.6654. Min Act: -0.1700

Data Index: 3068587 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.7104. Min Act: -0.1700

Data Index: 3421446 (Open Web Text)

Max Activating Token Index: 284

Text #2

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.5553. Min Act: -0.1699

Data Index: 5534682 (Open Web Text)

Max Activating Token Index: 164

Text #3

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.5651. Min Act: -0.1700

Data Index: 8537425 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6003. Min Act: -0.1700

Data Index: 751722 (Open Web Text)

Max Activating Token Index: 989

Text #5

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.5039. Min Act: -0.1700

Data Index: 1331160 (Open Web Text)

Max Activating Token Index: 721

Text #6

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6140. Min Act: -0.1700

Data Index: 72717 (Open Web Text)

Max Activating Token Index: 745

Text #7

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.4979. Min Act: -0.1700

Data Index: 4539802 (Open Web Text)

Max Activating Token Index: 192

Text #8

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.4743. Min Act: -0.1700

Data Index: 7377906 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.4542. Min Act: -0.1700

Data Index: 1814322 (Open Web Text)

Max Activating Token Index: 513

Text #10

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.6010. Min Act: -0.1700

Data Index: 321837 (Open Web Text)

Max Activating Token Index: 540

Text #11

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.4979. Min Act: -0.1700

Data Index: 5545381 (Open Web Text)

Max Activating Token Index: 282

Text #12

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1945213 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.4914. Min Act: -0.1700

Data Index: 7282367 (Open Web Text)

Max Activating Token Index: 828

Text #14

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.4164. Min Act: -0.1700

Data Index: 6852239 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.4777. Min Act: -0.1700

Data Index: 1858141 (Open Web Text)

Max Activating Token Index: 783

Text #16

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.5299. Min Act: -0.1700

Data Index: 3335970 (Open Web Text)

Max Activating Token Index: 35

Text #17

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.5256. Min Act: -0.1700

Data Index: 4517071 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.4636. Min Act: -0.1700

Data Index: 8456192 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.7104. Min Range: -3.7104

Max Act: 3.5117. Min Act: -0.1700

Data Index: 619340 (Open Web Text)

Max Activating Token Index: 329