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

Dataset: Open Web Text

Neuron 2840 in Layer 1

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: 1.2926. Min Range: -1.2926

Max Act: 1.2926. Min Act: -0.1700

Data Index: 5836691 (Open Web Text)

Max Activating Token Index: 226

Text #1

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2738. Min Act: -0.1700

Data Index: 2567000 (Open Web Text)

Max Activating Token Index: 196

Text #2

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2725. Min Act: -0.1700

Data Index: 1797081 (Open Web Text)

Max Activating Token Index: 484

Text #3

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2701. Min Act: -0.1700

Data Index: 2766040 (Open Web Text)

Max Activating Token Index: 619

Text #4

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2658. Min Act: -0.1700

Data Index: 1159337 (Open Web Text)

Max Activating Token Index: 364

Text #5

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2543. Min Act: -0.1700

Data Index: 1139311 (Open Web Text)

Max Activating Token Index: 148

Text #6

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2625. Min Act: -0.1700

Data Index: 8111429 (Open Web Text)

Max Activating Token Index: 921

Text #7

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2519. Min Act: -0.1700

Data Index: 6109804 (Open Web Text)

Max Activating Token Index: 491

Text #8

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2531. Min Act: -0.1700

Data Index: 5637511 (Open Web Text)

Max Activating Token Index: 811

Text #9

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2467. Min Act: -0.1700

Data Index: 6846260 (Open Web Text)

Max Activating Token Index: 510

Text #10

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2442. Min Act: -0.1700

Data Index: 851812 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2402. Min Act: -0.1700

Data Index: 7242795 (Open Web Text)

Max Activating Token Index: 803

Text #12

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2329. Min Act: -0.1700

Data Index: 5637513 (Open Web Text)

Max Activating Token Index: 708

Text #13

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2347. Min Act: -0.1700

Data Index: 7889231 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2232. Min Act: -0.1700

Data Index: 298720 (Open Web Text)

Max Activating Token Index: 435

Text #15

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2210. Min Act: -0.1700

Data Index: 3355405 (Open Web Text)

Max Activating Token Index: 908

Text #16

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2220. Min Act: -0.1700

Data Index: 1068354 (Open Web Text)

Max Activating Token Index: 824

Text #17

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2278. Min Act: -0.1700

Data Index: 3355409 (Open Web Text)

Max Activating Token Index: 754

Text #18

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2267. Min Act: -0.1700

Data Index: 298722 (Open Web Text)

Max Activating Token Index: 88

Text #19

Max Range: 1.2926. Min Range: -1.2926

Max Act: 1.2200. Min Act: -0.1700

Data Index: 4264345 (Open Web Text)

Max Activating Token Index: 937