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

Dataset: Open Web Text

Neuron 515 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: 4.2925. Min Range: -4.2925

Max Act: 4.2925. Min Act: -0.1700

Data Index: 1387989 (Open Web Text)

Max Activating Token Index: 491

Text #1

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.2074. Min Act: -0.1700

Data Index: 7609616 (Open Web Text)

Max Activating Token Index: 974

Text #2

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.2055. Min Act: -0.1700

Data Index: 6494301 (Open Web Text)

Max Activating Token Index: 797

Text #3

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.1470. Min Act: -0.1700

Data Index: 6092633 (Open Web Text)

Max Activating Token Index: 946

Text #4

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.1529. Min Act: -0.1700

Data Index: 695588 (Open Web Text)

Max Activating Token Index: 666

Text #5

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.1042. Min Act: -0.1700

Data Index: 2929407 (Open Web Text)

Max Activating Token Index: 621

Text #6

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0888. Min Act: -0.1700

Data Index: 7317012 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0965. Min Act: -0.1700

Data Index: 7521735 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.1097. Min Act: -0.1700

Data Index: 1982023 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0875. Min Act: -0.1700

Data Index: 2735215 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0549. Min Act: -0.1700

Data Index: 6350874 (Open Web Text)

Max Activating Token Index: 847

Text #11

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0715. Min Act: -0.1700

Data Index: 1317267 (Open Web Text)

Max Activating Token Index: 38

Text #12

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0902. Min Act: -0.1700

Data Index: 14115 (Open Web Text)

Max Activating Token Index: 41

Text #13

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0617. Min Act: -0.1700

Data Index: 5296624 (Open Web Text)

Max Activating Token Index: 986

Text #14

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0656. Min Act: -0.1700

Data Index: 7864217 (Open Web Text)

Max Activating Token Index: 175

Text #15

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0322. Min Act: -0.1700

Data Index: 2910448 (Open Web Text)

Max Activating Token Index: 731

Text #16

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0208. Min Act: -0.1700

Data Index: 1064674 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0303. Min Act: -0.1700

Data Index: 1762365 (Open Web Text)

Max Activating Token Index: 757

Text #18

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0698. Min Act: -0.1700

Data Index: 254435 (Open Web Text)

Max Activating Token Index: 538

Text #19

Max Range: 4.2925. Min Range: -4.2925

Max Act: 4.0215. Min Act: -0.1700

Data Index: 2500521 (Open Web Text)

Max Activating Token Index: 246