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

Dataset: Open Web Text

Neuron 1294 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: 1.2584. Min Range: -1.2584

Max Act: 1.2575. Min Act: -0.1700

Data Index: 6285458 (Open Web Text)

Max Activating Token Index: 357

Text #1

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2575. Min Act: -0.1700

Data Index: 7861067 (Open Web Text)

Max Activating Token Index: 435

Text #2

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2516. Min Act: -0.1695

Data Index: 1249863 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2457. Min Act: -0.1699

Data Index: 101776 (Open Web Text)

Max Activating Token Index: 588

Text #4

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2558. Min Act: -0.1700

Data Index: 4023410 (Open Web Text)

Max Activating Token Index: 680

Text #5

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2584. Min Act: -0.1700

Data Index: 5319103 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2353. Min Act: -0.1700

Data Index: 118889 (Open Web Text)

Max Activating Token Index: 977

Text #7

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2426. Min Act: -0.1699

Data Index: 923365 (Open Web Text)

Max Activating Token Index: 921

Text #8

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2440. Min Act: -0.1700

Data Index: 3876399 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2483. Min Act: -0.1700

Data Index: 982822 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2552. Min Act: -0.1700

Data Index: 2747761 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2304. Min Act: -0.1698

Data Index: 3481440 (Open Web Text)

Max Activating Token Index: 353

Text #12

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2324. Min Act: -0.1700

Data Index: 647981 (Open Web Text)

Max Activating Token Index: 55

Text #13

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2305. Min Act: -0.1700

Data Index: 8008944 (Open Web Text)

Max Activating Token Index: 668

Text #14

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2302. Min Act: -0.1699

Data Index: 7067449 (Open Web Text)

Max Activating Token Index: 974

Text #15

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2223. Min Act: -0.1693

Data Index: 3302787 (Open Web Text)

Max Activating Token Index: 898

Text #16

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2305. Min Act: -0.1696

Data Index: 4690503 (Open Web Text)

Max Activating Token Index: 923

Text #17

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2239. Min Act: -0.1700

Data Index: 2228230 (Open Web Text)

Max Activating Token Index: 620

Text #18

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2100. Min Act: -0.1700

Data Index: 7950262 (Open Web Text)

Max Activating Token Index: 917

Text #19

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2140. Min Act: -0.1699

Data Index: 1297506 (Open Web Text)

Max Activating Token Index: 541