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

Dataset: Open Web Text

Neuron 2123 in Layer 5

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: 3.0912. Min Range: -3.0912

Max Act: 3.0912. Min Act: -0.1700

Data Index: 4153303 (Open Web Text)

Max Activating Token Index: 813

Text #1

Max Range: 3.0912. Min Range: -3.0912

Max Act: 3.0260. Min Act: -0.1700

Data Index: 2611445 (Open Web Text)

Max Activating Token Index: 305

Text #2

Max Range: 3.0912. Min Range: -3.0912

Max Act: 3.0417. Min Act: -0.1700

Data Index: 7947436 (Open Web Text)

Max Activating Token Index: 769

Text #3

Max Range: 3.0912. Min Range: -3.0912

Max Act: 3.0405. Min Act: -0.1700

Data Index: 4339062 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 3.0912. Min Range: -3.0912

Max Act: 3.0123. Min Act: -0.1700

Data Index: 7368794 (Open Web Text)

Max Activating Token Index: 485

Text #5

Max Range: 3.0912. Min Range: -3.0912

Max Act: 3.0057. Min Act: -0.1700

Data Index: 398444 (Open Web Text)

Max Activating Token Index: 491

Text #6

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.9593. Min Act: -0.1700

Data Index: 8114037 (Open Web Text)

Max Activating Token Index: 765

Text #7

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.9552. Min Act: -0.1700

Data Index: 4443758 (Open Web Text)

Max Activating Token Index: 633

Text #8

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.9440. Min Act: -0.1700

Data Index: 1782690 (Open Web Text)

Max Activating Token Index: 839

Text #9

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.9528. Min Act: -0.1700

Data Index: 8005325 (Open Web Text)

Max Activating Token Index: 879

Text #10

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.9315. Min Act: -0.1700

Data Index: 1934576 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.8980. Min Act: -0.1700

Data Index: 7238235 (Open Web Text)

Max Activating Token Index: 322

Text #12

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.9313. Min Act: -0.1700

Data Index: 4648929 (Open Web Text)

Max Activating Token Index: 194

Text #13

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.8998. Min Act: -0.1700

Data Index: 2385328 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.8940. Min Act: -0.1700

Data Index: 6872958 (Open Web Text)

Max Activating Token Index: 915

Text #15

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.8899. Min Act: -0.1700

Data Index: 3109431 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.8789. Min Act: -0.1700

Data Index: 5522012 (Open Web Text)

Max Activating Token Index: 448

Text #17

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.9116. Min Act: -0.1700

Data Index: 5259861 (Open Web Text)

Max Activating Token Index: 302

Text #18

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.9064. Min Act: -0.1700

Data Index: 3446094 (Open Web Text)

Max Activating Token Index: 916

Text #19

Max Range: 3.0912. Min Range: -3.0912

Max Act: 2.8802. Min Act: -0.1700

Data Index: 1327861 (Open Web Text)

Max Activating Token Index: 550