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

Dataset: Open Web Text

Neuron 977 in Layer 6

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: 5.5036. Min Range: -5.5036

Max Act: 5.5036. Min Act: -0.1700

Data Index: 8027636 (Open Web Text)

Max Activating Token Index: 428

Text #1

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.4051. Min Act: -0.1700

Data Index: 6588026 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.4101. Min Act: -0.1700

Data Index: 189577 (Open Web Text)

Max Activating Token Index: 319

Text #3

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.2921. Min Act: -0.1700

Data Index: 8533336 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.3086. Min Act: -0.1700

Data Index: 1576517 (Open Web Text)

Max Activating Token Index: 516

Text #5

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.3403. Min Act: -0.1700

Data Index: 7552149 (Open Web Text)

Max Activating Token Index: 771

Text #6

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.2619. Min Act: -0.1700

Data Index: 2973535 (Open Web Text)

Max Activating Token Index: 1011

Text #7

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.2819. Min Act: -0.1700

Data Index: 7216852 (Open Web Text)

Max Activating Token Index: 181

Text #8

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.2535. Min Act: -0.1700

Data Index: 8198572 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.1905. Min Act: -0.1700

Data Index: 7980287 (Open Web Text)

Max Activating Token Index: 612

Text #10

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.1651. Min Act: -0.1700

Data Index: 6001671 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.2193. Min Act: -0.1700

Data Index: 5109758 (Open Web Text)

Max Activating Token Index: 659

Text #12

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.1970. Min Act: -0.1700

Data Index: 4790012 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.2654. Min Act: -0.1700

Data Index: 6268542 (Open Web Text)

Max Activating Token Index: 392

Text #14

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.1732. Min Act: -0.1700

Data Index: 4618077 (Open Web Text)

Max Activating Token Index: 669

Text #15

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.1858. Min Act: -0.1700

Data Index: 7064133 (Open Web Text)

Max Activating Token Index: 867

Text #16

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.1865. Min Act: -0.1700

Data Index: 1336818 (Open Web Text)

Max Activating Token Index: 698

Text #17

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.1816. Min Act: -0.1700

Data Index: 5431613 (Open Web Text)

Max Activating Token Index: 921

Text #18

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.1245. Min Act: -0.1700

Data Index: 8128444 (Open Web Text)

Max Activating Token Index: 620

Text #19

Max Range: 5.5036. Min Range: -5.5036

Max Act: 5.1539. Min Act: -0.1700

Data Index: 3648490 (Open Web Text)

Max Activating Token Index: 111