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

Dataset: Open Web Text

Neuron 2611 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: 3.4601. Min Range: -3.4601

Max Act: 3.4601. Min Act: -0.1700

Data Index: 3139069 (Open Web Text)

Max Activating Token Index: 369

Text #1

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.4092. Min Act: -0.1700

Data Index: 7349197 (Open Web Text)

Max Activating Token Index: 826

Text #2

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.3300. Min Act: -0.1700

Data Index: 5778682 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.2990. Min Act: -0.1700

Data Index: 598414 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.2937. Min Act: -0.1700

Data Index: 1747344 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.2275. Min Act: -0.1700

Data Index: 3860978 (Open Web Text)

Max Activating Token Index: 981

Text #6

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.2157. Min Act: -0.1700

Data Index: 4983158 (Open Web Text)

Max Activating Token Index: 865

Text #7

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.2137. Min Act: -0.1700

Data Index: 7237782 (Open Web Text)

Max Activating Token Index: 985

Text #8

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1948. Min Act: -0.1700

Data Index: 341667 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1924. Min Act: -0.1700

Data Index: 1466257 (Open Web Text)

Max Activating Token Index: 903

Text #10

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1946. Min Act: -0.1700

Data Index: 6347801 (Open Web Text)

Max Activating Token Index: 990

Text #11

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1819. Min Act: -0.1700

Data Index: 7196494 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1933. Min Act: -0.1700

Data Index: 2825850 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1743. Min Act: -0.1700

Data Index: 3339276 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1816. Min Act: -0.1700

Data Index: 323053 (Open Web Text)

Max Activating Token Index: 572

Text #15

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1577. Min Act: -0.1700

Data Index: 1115599 (Open Web Text)

Max Activating Token Index: 646

Text #16

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1587. Min Act: -0.1700

Data Index: 3508886 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1422. Min Act: -0.1700

Data Index: 4325173 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1635. Min Act: -0.1700

Data Index: 4350504 (Open Web Text)

Max Activating Token Index: 527

Text #19

Max Range: 3.4601. Min Range: -3.4601

Max Act: 3.1370. Min Act: -0.1700

Data Index: 6474415 (Open Web Text)

Max Activating Token Index: 916