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

Dataset: Open Web Text

Neuron 2352 in Layer 6

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: 3.2938. Min Range: -3.2938

Max Act: 3.2827. Min Act: -0.1700

Data Index: 197608 (Open Web Text)

Max Activating Token Index: 352

Text #1

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2861. Min Act: -0.1700

Data Index: 4220621 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2800. Min Act: -0.1700

Data Index: 1715085 (Open Web Text)

Max Activating Token Index: 1017

Text #3

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2938. Min Act: -0.1700

Data Index: 3252825 (Open Web Text)

Max Activating Token Index: 324

Text #4

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2669. Min Act: -0.1700

Data Index: 2744831 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2606. Min Act: -0.1700

Data Index: 6749019 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2529. Min Act: -0.1700

Data Index: 4005066 (Open Web Text)

Max Activating Token Index: 70

Text #7

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2435. Min Act: -0.1700

Data Index: 7162332 (Open Web Text)

Max Activating Token Index: 832

Text #8

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2366. Min Act: -0.1700

Data Index: 4815445 (Open Web Text)

Max Activating Token Index: 837

Text #9

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2547. Min Act: -0.1700

Data Index: 4031183 (Open Web Text)

Max Activating Token Index: 1005

Text #10

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2411. Min Act: -0.1700

Data Index: 7515433 (Open Web Text)

Max Activating Token Index: 197

Text #11

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2503. Min Act: -0.1700

Data Index: 2502207 (Open Web Text)

Max Activating Token Index: 62

Text #12

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2458. Min Act: -0.1700

Data Index: 2192901 (Open Web Text)

Max Activating Token Index: 1009

Text #13

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2298. Min Act: -0.1700

Data Index: 1860825 (Open Web Text)

Max Activating Token Index: 937

Text #14

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2417. Min Act: -0.1700

Data Index: 1195922 (Open Web Text)

Max Activating Token Index: 389

Text #15

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2107. Min Act: -0.1700

Data Index: 7452640 (Open Web Text)

Max Activating Token Index: 770

Text #16

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1799128 (Open Web Text)

Max Activating Token Index: 424

Text #17

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2020. Min Act: -0.1700

Data Index: 3936325 (Open Web Text)

Max Activating Token Index: 905

Text #18

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.2122. Min Act: -0.1700

Data Index: 1909359 (Open Web Text)

Max Activating Token Index: 498

Text #19

Max Range: 3.2938. Min Range: -3.2938

Max Act: 3.1983. Min Act: -0.1700

Data Index: 1702403 (Open Web Text)

Max Activating Token Index: 159