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

Dataset: Open Web Text

Neuron 1026 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: 2.2446. Min Range: -2.2446

Max Act: 2.2446. Min Act: -0.1700

Data Index: 3046224 (Open Web Text)

Max Activating Token Index: 214

Text #1

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.2110. Min Act: -0.1700

Data Index: 4800143 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.2218. Min Act: -0.1700

Data Index: 2493382 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.2114. Min Act: -0.1700

Data Index: 2736995 (Open Web Text)

Max Activating Token Index: 51

Text #4

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1959. Min Act: -0.1700

Data Index: 7439682 (Open Web Text)

Max Activating Token Index: 295

Text #5

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1948. Min Act: -0.1700

Data Index: 3363775 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.2046. Min Act: -0.1700

Data Index: 5241472 (Open Web Text)

Max Activating Token Index: 48

Text #7

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1990. Min Act: -0.1700

Data Index: 1229981 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1875. Min Act: -0.1700

Data Index: 6484065 (Open Web Text)

Max Activating Token Index: 357

Text #9

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.2004. Min Act: -0.1700

Data Index: 7965708 (Open Web Text)

Max Activating Token Index: 199

Text #10

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1873. Min Act: -0.1700

Data Index: 2729886 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1762. Min Act: -0.1700

Data Index: 6779462 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1850. Min Act: -0.1700

Data Index: 843588 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1701. Min Act: -0.1700

Data Index: 639321 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1777. Min Act: -0.1700

Data Index: 7814664 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1823. Min Act: -0.1700

Data Index: 3256709 (Open Web Text)

Max Activating Token Index: 99

Text #16

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1765. Min Act: -0.1700

Data Index: 6922334 (Open Web Text)

Max Activating Token Index: 620

Text #17

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1790. Min Act: -0.1700

Data Index: 4186580 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1718. Min Act: -0.1700

Data Index: 6580964 (Open Web Text)

Max Activating Token Index: 849

Text #19

Max Range: 2.2446. Min Range: -2.2446

Max Act: 2.1639. Min Act: -0.1700

Data Index: 6648954 (Open Web Text)

Max Activating Token Index: 390