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

Dataset: Open Web Text

Neuron 79 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: 4.4060. Min Range: -4.4060

Max Act: 4.4060. Min Act: -0.1700

Data Index: 5935753 (Open Web Text)

Max Activating Token Index: 120

Text #1

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.3654. Min Act: -0.1700

Data Index: 3199780 (Open Web Text)

Max Activating Token Index: 255

Text #2

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2935. Min Act: -0.1700

Data Index: 648837 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2888. Min Act: -0.1700

Data Index: 578725 (Open Web Text)

Max Activating Token Index: 370

Text #4

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2983. Min Act: -0.1700

Data Index: 8048810 (Open Web Text)

Max Activating Token Index: 169

Text #5

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2704. Min Act: -0.1700

Data Index: 7115851 (Open Web Text)

Max Activating Token Index: 377

Text #6

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2384. Min Act: -0.1700

Data Index: 648838 (Open Web Text)

Max Activating Token Index: 696

Text #7

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2531. Min Act: -0.1700

Data Index: 7142332 (Open Web Text)

Max Activating Token Index: 508

Text #8

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2392. Min Act: -0.1700

Data Index: 6904352 (Open Web Text)

Max Activating Token Index: 446

Text #9

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2418. Min Act: -0.1700

Data Index: 1875511 (Open Web Text)

Max Activating Token Index: 600

Text #10

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2019. Min Act: -0.1700

Data Index: 4658061 (Open Web Text)

Max Activating Token Index: 512

Text #11

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2123. Min Act: -0.1700

Data Index: 2908797 (Open Web Text)

Max Activating Token Index: 228

Text #12

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2152. Min Act: -0.1700

Data Index: 745104 (Open Web Text)

Max Activating Token Index: 632

Text #13

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2210. Min Act: -0.1700

Data Index: 6083973 (Open Web Text)

Max Activating Token Index: 739

Text #14

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2178. Min Act: -0.1700

Data Index: 3619675 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2128. Min Act: -0.1700

Data Index: 4167520 (Open Web Text)

Max Activating Token Index: 48

Text #16

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.1806. Min Act: -0.1700

Data Index: 170175 (Open Web Text)

Max Activating Token Index: 280

Text #17

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.2016. Min Act: -0.1700

Data Index: 305805 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.1799. Min Act: -0.1700

Data Index: 1298174 (Open Web Text)

Max Activating Token Index: 452

Text #19

Max Range: 4.4060. Min Range: -4.4060

Max Act: 4.1678. Min Act: -0.1700

Data Index: 836847 (Open Web Text)

Max Activating Token Index: 803