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

Dataset: Open Web Text

Neuron 2104 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: 6.5358. Min Range: -6.5358

Max Act: 6.5358. Min Act: -0.1700

Data Index: 371188 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.5103. Min Act: -0.1700

Data Index: 7473328 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.4173. Min Act: -0.1700

Data Index: 8368592 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.4295. Min Act: -0.1700

Data Index: 7608499 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.4302. Min Act: -0.1700

Data Index: 3101007 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.3090. Min Act: -0.1700

Data Index: 7029976 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.3001. Min Act: -0.1700

Data Index: 2118083 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2944. Min Act: -0.1700

Data Index: 3718163 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2930. Min Act: -0.1700

Data Index: 7385460 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2873. Min Act: -0.1700

Data Index: 2040231 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2839. Min Act: -0.1700

Data Index: 4890103 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2733. Min Act: -0.1700

Data Index: 368018 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2835. Min Act: -0.1700

Data Index: 7888544 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2503. Min Act: -0.1699

Data Index: 2193837 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2387. Min Act: -0.1700

Data Index: 2221306 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2551. Min Act: -0.1700

Data Index: 4049112 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2699. Min Act: -0.1700

Data Index: 3849639 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2504. Min Act: -0.1700

Data Index: 7841808 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2607. Min Act: -0.1700

Data Index: 974236 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 6.5358. Min Range: -6.5358

Max Act: 6.2385. Min Act: -0.1700

Data Index: 3774760 (Open Web Text)

Max Activating Token Index: 5