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

Dataset: Open Web Text

Neuron 1958 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: 4.9520. Min Range: -4.9520

Max Act: 4.9520. Min Act: -0.1700

Data Index: 5171936 (Open Web Text)

Max Activating Token Index: 599

Text #1

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.8898. Min Act: -0.1700

Data Index: 6709548 (Open Web Text)

Max Activating Token Index: 1013

Text #2

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.8619. Min Act: -0.1700

Data Index: 5956504 (Open Web Text)

Max Activating Token Index: 413

Text #3

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.8913. Min Act: -0.1700

Data Index: 6602525 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.8172. Min Act: -0.1700

Data Index: 7438447 (Open Web Text)

Max Activating Token Index: 928

Text #5

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7457. Min Act: -0.1700

Data Index: 790476 (Open Web Text)

Max Activating Token Index: 412

Text #6

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7620. Min Act: -0.1700

Data Index: 5504274 (Open Web Text)

Max Activating Token Index: 205

Text #7

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7806. Min Act: -0.1700

Data Index: 8067321 (Open Web Text)

Max Activating Token Index: 225

Text #8

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7486. Min Act: -0.1700

Data Index: 2503554 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7579. Min Act: -0.1700

Data Index: 6475731 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7291. Min Act: -0.1700

Data Index: 5179901 (Open Web Text)

Max Activating Token Index: 634

Text #11

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7679. Min Act: -0.1700

Data Index: 2751086 (Open Web Text)

Max Activating Token Index: 779

Text #12

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.6993. Min Act: -0.1700

Data Index: 895384 (Open Web Text)

Max Activating Token Index: 879

Text #13

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7100. Min Act: -0.1700

Data Index: 6757775 (Open Web Text)

Max Activating Token Index: 78

Text #14

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7557. Min Act: -0.1700

Data Index: 3311270 (Open Web Text)

Max Activating Token Index: 635

Text #15

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7521. Min Act: -0.1700

Data Index: 4901248 (Open Web Text)

Max Activating Token Index: 303

Text #16

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7279. Min Act: -0.1700

Data Index: 5504273 (Open Web Text)

Max Activating Token Index: 1006

Text #17

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7341. Min Act: -0.1700

Data Index: 3830909 (Open Web Text)

Max Activating Token Index: 210

Text #18

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.6983. Min Act: -0.1700

Data Index: 6874290 (Open Web Text)

Max Activating Token Index: 392

Text #19

Max Range: 4.9520. Min Range: -4.9520

Max Act: 4.7209. Min Act: -0.1700

Data Index: 4290317 (Open Web Text)

Max Activating Token Index: 575