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

Dataset: Open Web Text

Neuron 2005 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: 3.6513. Min Range: -3.6513

Max Act: 3.6513. Min Act: -0.1700

Data Index: 5709357 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.6076. Min Act: -0.1700

Data Index: 7647352 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.5815. Min Act: -0.1700

Data Index: 4297216 (Open Web Text)

Max Activating Token Index: 103

Text #3

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.5547. Min Act: -0.1700

Data Index: 44267 (Open Web Text)

Max Activating Token Index: 473

Text #4

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.5358. Min Act: -0.1700

Data Index: 55809 (Open Web Text)

Max Activating Token Index: 786

Text #5

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.5053. Min Act: -0.1700

Data Index: 7742351 (Open Web Text)

Max Activating Token Index: 625

Text #6

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.5076. Min Act: -0.1700

Data Index: 2916001 (Open Web Text)

Max Activating Token Index: 76

Text #7

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.5212. Min Act: -0.1700

Data Index: 5445161 (Open Web Text)

Max Activating Token Index: 186

Text #8

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.5139. Min Act: -0.1700

Data Index: 3258422 (Open Web Text)

Max Activating Token Index: 66

Text #9

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.5062. Min Act: -0.1700

Data Index: 5205427 (Open Web Text)

Max Activating Token Index: 882

Text #10

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4995. Min Act: -0.1700

Data Index: 8617565 (Open Web Text)

Max Activating Token Index: 976

Text #11

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4630. Min Act: -0.1700

Data Index: 6341401 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4843. Min Act: -0.1700

Data Index: 7638897 (Open Web Text)

Max Activating Token Index: 101

Text #13

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4515. Min Act: -0.1700

Data Index: 932045 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4534. Min Act: -0.1700

Data Index: 932032 (Open Web Text)

Max Activating Token Index: 56

Text #15

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4463. Min Act: -0.1700

Data Index: 8560057 (Open Web Text)

Max Activating Token Index: 345

Text #16

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4680. Min Act: -0.1700

Data Index: 2916000 (Open Web Text)

Max Activating Token Index: 842

Text #17

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4516. Min Act: -0.1700

Data Index: 6952824 (Open Web Text)

Max Activating Token Index: 339

Text #18

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4643. Min Act: -0.1700

Data Index: 3216737 (Open Web Text)

Max Activating Token Index: 72

Text #19

Max Range: 3.6513. Min Range: -3.6513

Max Act: 3.4539. Min Act: -0.1700

Data Index: 4282841 (Open Web Text)

Max Activating Token Index: 99