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

Dataset: Open Web Text

Neuron 3022 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: 4.2333. Min Range: -4.2333

Max Act: 4.2333. Min Act: -0.1700

Data Index: 8572 (Open Web Text)

Max Activating Token Index: 737

Text #1

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.2253. Min Act: -0.1700

Data Index: 7899591 (Open Web Text)

Max Activating Token Index: 818

Text #2

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1903. Min Act: -0.1700

Data Index: 2808283 (Open Web Text)

Max Activating Token Index: 608

Text #3

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.2061. Min Act: -0.1700

Data Index: 2935546 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.2216. Min Act: -0.1700

Data Index: 6987678 (Open Web Text)

Max Activating Token Index: 683

Text #5

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.2028. Min Act: -0.1700

Data Index: 2223229 (Open Web Text)

Max Activating Token Index: 773

Text #6

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1626. Min Act: -0.1700

Data Index: 907366 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1523. Min Act: -0.1700

Data Index: 5801766 (Open Web Text)

Max Activating Token Index: 423

Text #8

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1321. Min Act: -0.1700

Data Index: 5539806 (Open Web Text)

Max Activating Token Index: 949

Text #9

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1442. Min Act: -0.1700

Data Index: 7528363 (Open Web Text)

Max Activating Token Index: 861

Text #10

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1186. Min Act: -0.1700

Data Index: 7552416 (Open Web Text)

Max Activating Token Index: 353

Text #11

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1016. Min Act: -0.1700

Data Index: 7379501 (Open Web Text)

Max Activating Token Index: 769

Text #12

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1136. Min Act: -0.1700

Data Index: 8734512 (Open Web Text)

Max Activating Token Index: 121

Text #13

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1361. Min Act: -0.1700

Data Index: 481610 (Open Web Text)

Max Activating Token Index: 392

Text #14

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1209. Min Act: -0.1700

Data Index: 1489579 (Open Web Text)

Max Activating Token Index: 483

Text #15

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.0731. Min Act: -0.1700

Data Index: 2246433 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.1020. Min Act: -0.1700

Data Index: 349709 (Open Web Text)

Max Activating Token Index: 684

Text #17

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.0715. Min Act: -0.1700

Data Index: 6562909 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.0745. Min Act: -0.1700

Data Index: 1233935 (Open Web Text)

Max Activating Token Index: 518

Text #19

Max Range: 4.2333. Min Range: -4.2333

Max Act: 4.0963. Min Act: -0.1700

Data Index: 7183933 (Open Web Text)

Max Activating Token Index: 736