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

Dataset: Open Web Text

Neuron 230 in Layer 2

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: 1.7914. Min Range: -1.7914

Max Act: 1.7914. Min Act: -0.1700

Data Index: 347510 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.7081. Min Act: -0.1700

Data Index: 1717228 (Open Web Text)

Max Activating Token Index: 568

Text #2

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6797. Min Act: -0.1700

Data Index: 6568406 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6824. Min Act: -0.1700

Data Index: 4490061 (Open Web Text)

Max Activating Token Index: 464

Text #4

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6664. Min Act: -0.1700

Data Index: 3100641 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6596. Min Act: -0.1700

Data Index: 2199587 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6506. Min Act: -0.1700

Data Index: 3746701 (Open Web Text)

Max Activating Token Index: 805

Text #7

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6557. Min Act: -0.1700

Data Index: 3709052 (Open Web Text)

Max Activating Token Index: 906

Text #8

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6407. Min Act: -0.1700

Data Index: 5395302 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6371. Min Act: -0.1700

Data Index: 4282148 (Open Web Text)

Max Activating Token Index: 186

Text #10

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6436. Min Act: -0.1700

Data Index: 2982451 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6418. Min Act: -0.1700

Data Index: 3570536 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6211. Min Act: -0.1700

Data Index: 2598369 (Open Web Text)

Max Activating Token Index: 847

Text #13

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6358. Min Act: -0.1700

Data Index: 817733 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6384. Min Act: -0.1700

Data Index: 2626002 (Open Web Text)

Max Activating Token Index: 569

Text #15

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6125. Min Act: -0.1700

Data Index: 3047902 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6275. Min Act: -0.1700

Data Index: 5712967 (Open Web Text)

Max Activating Token Index: 746

Text #17

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6299. Min Act: -0.1700

Data Index: 2774325 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6245. Min Act: -0.1700

Data Index: 1501803 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 1.7914. Min Range: -1.7914

Max Act: 1.6233. Min Act: -0.1700

Data Index: 8100441 (Open Web Text)

Max Activating Token Index: 715