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

Dataset: Open Web Text

Neuron 1935 in Layer 3

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: 1.7719. Min Range: -1.7719

Max Act: 1.7641. Min Act: -0.1700

Data Index: 6943132 (Open Web Text)

Max Activating Token Index: 450

Text #1

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7700. Min Act: -0.1700

Data Index: 5890954 (Open Web Text)

Max Activating Token Index: 57

Text #2

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7648. Min Act: -0.1699

Data Index: 6667794 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7719. Min Act: -0.1700

Data Index: 8736464 (Open Web Text)

Max Activating Token Index: 503

Text #4

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7462. Min Act: -0.1700

Data Index: 8736466 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7469. Min Act: -0.1700

Data Index: 2947871 (Open Web Text)

Max Activating Token Index: 867

Text #6

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7525. Min Act: -0.1700

Data Index: 4881305 (Open Web Text)

Max Activating Token Index: 931

Text #7

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7190. Min Act: -0.1700

Data Index: 3147244 (Open Web Text)

Max Activating Token Index: 948

Text #8

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7399. Min Act: -0.1700

Data Index: 2378686 (Open Web Text)

Max Activating Token Index: 450

Text #9

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7126. Min Act: -0.1698

Data Index: 6491984 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7293. Min Act: -0.1699

Data Index: 5099105 (Open Web Text)

Max Activating Token Index: 43

Text #11

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7125. Min Act: -0.1700

Data Index: 5940391 (Open Web Text)

Max Activating Token Index: 44

Text #12

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7264. Min Act: -0.1700

Data Index: 1988400 (Open Web Text)

Max Activating Token Index: 434

Text #13

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7043. Min Act: -0.1700

Data Index: 3147240 (Open Web Text)

Max Activating Token Index: 697

Text #14

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7068. Min Act: -0.1700

Data Index: 5694339 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.6956. Min Act: -0.1700

Data Index: 5786540 (Open Web Text)

Max Activating Token Index: 948

Text #16

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7146. Min Act: -0.1698

Data Index: 3369570 (Open Web Text)

Max Activating Token Index: 1017

Text #17

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7087. Min Act: -0.1691

Data Index: 5544314 (Open Web Text)

Max Activating Token Index: 359

Text #18

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.6941. Min Act: -0.1699

Data Index: 5989338 (Open Web Text)

Max Activating Token Index: 141

Text #19

Max Range: 1.7719. Min Range: -1.7719

Max Act: 1.7029. Min Act: -0.1700

Data Index: 6126802 (Open Web Text)

Max Activating Token Index: 11