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

Dataset: Open Web Text

Neuron 1360 in Layer 0

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: 1.2834. Min Range: -1.2834

Max Act: 1.2834. Min Act: -0.1700

Data Index: 8180350 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2555. Min Act: -0.1700

Data Index: 4790436 (Open Web Text)

Max Activating Token Index: 764

Text #2

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2479. Min Act: -0.1700

Data Index: 6490977 (Open Web Text)

Max Activating Token Index: 777

Text #3

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2360. Min Act: -0.1700

Data Index: 1351054 (Open Web Text)

Max Activating Token Index: 777

Text #4

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2320. Min Act: -0.1700

Data Index: 654520 (Open Web Text)

Max Activating Token Index: 760

Text #5

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2311. Min Act: -0.1700

Data Index: 6135286 (Open Web Text)

Max Activating Token Index: 776

Text #6

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2318. Min Act: -0.1700

Data Index: 5771401 (Open Web Text)

Max Activating Token Index: 782

Text #7

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2400. Min Act: -0.1700

Data Index: 1267016 (Open Web Text)

Max Activating Token Index: 767

Text #8

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2320. Min Act: -0.1700

Data Index: 617995 (Open Web Text)

Max Activating Token Index: 772

Text #9

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2340. Min Act: -0.1700

Data Index: 8440447 (Open Web Text)

Max Activating Token Index: 777

Text #10

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2399. Min Act: -0.1700

Data Index: 4477736 (Open Web Text)

Max Activating Token Index: 774

Text #11

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2367. Min Act: -0.1700

Data Index: 982266 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2307. Min Act: -0.1700

Data Index: 4477732 (Open Web Text)

Max Activating Token Index: 764

Text #13

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2181. Min Act: -0.1700

Data Index: 3221437 (Open Web Text)

Max Activating Token Index: 782

Text #14

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2139. Min Act: -0.1700

Data Index: 4477744 (Open Web Text)

Max Activating Token Index: 770

Text #15

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2186. Min Act: -0.1700

Data Index: 5406318 (Open Web Text)

Max Activating Token Index: 769

Text #16

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2157. Min Act: -0.1700

Data Index: 1842323 (Open Web Text)

Max Activating Token Index: 764

Text #17

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2238. Min Act: -0.1700

Data Index: 3779936 (Open Web Text)

Max Activating Token Index: 778

Text #18

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2141. Min Act: -0.1700

Data Index: 699612 (Open Web Text)

Max Activating Token Index: 771

Text #19

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2252. Min Act: -0.1700

Data Index: 6488607 (Open Web Text)

Max Activating Token Index: 757