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

Dataset: Open Web Text

Neuron 1761 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: 6.0474. Min Range: -6.0474

Max Act: 6.0474. Min Act: -0.1700

Data Index: 7713454 (Open Web Text)

Max Activating Token Index: 450

Text #1

Max Range: 6.0474. Min Range: -6.0474

Max Act: 6.0465. Min Act: -0.1700

Data Index: 8395841 (Open Web Text)

Max Activating Token Index: 27

Text #2

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.9456. Min Act: -0.1700

Data Index: 4907640 (Open Web Text)

Max Activating Token Index: 767

Text #3

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.8961. Min Act: -0.1700

Data Index: 3456868 (Open Web Text)

Max Activating Token Index: 665

Text #4

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.8512. Min Act: -0.1700

Data Index: 7093883 (Open Web Text)

Max Activating Token Index: 1015

Text #5

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7785. Min Act: -0.1700

Data Index: 2488507 (Open Web Text)

Max Activating Token Index: 905

Text #6

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.8335. Min Act: -0.1700

Data Index: 2875562 (Open Web Text)

Max Activating Token Index: 213

Text #7

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.8458. Min Act: -0.1700

Data Index: 913919 (Open Web Text)

Max Activating Token Index: 369

Text #8

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7746. Min Act: -0.1700

Data Index: 4285019 (Open Web Text)

Max Activating Token Index: 1011

Text #9

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.8255. Min Act: -0.1700

Data Index: 7693719 (Open Web Text)

Max Activating Token Index: 95

Text #10

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7595. Min Act: -0.1700

Data Index: 4894606 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7672. Min Act: -0.1700

Data Index: 6894117 (Open Web Text)

Max Activating Token Index: 725

Text #12

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7679. Min Act: -0.1700

Data Index: 3720599 (Open Web Text)

Max Activating Token Index: 190

Text #13

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7384. Min Act: -0.1700

Data Index: 1711480 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7241. Min Act: -0.1700

Data Index: 4184881 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.6893. Min Act: -0.1700

Data Index: 5225560 (Open Web Text)

Max Activating Token Index: 906

Text #16

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7464. Min Act: -0.1700

Data Index: 4715044 (Open Web Text)

Max Activating Token Index: 311

Text #17

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7226. Min Act: -0.1700

Data Index: 5889299 (Open Web Text)

Max Activating Token Index: 440

Text #18

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.7590. Min Act: -0.1700

Data Index: 4664810 (Open Web Text)

Max Activating Token Index: 417

Text #19

Max Range: 6.0474. Min Range: -6.0474

Max Act: 5.6663. Min Act: -0.1700

Data Index: 2364283 (Open Web Text)

Max Activating Token Index: 595