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

Dataset: Open Web Text

Neuron 1260 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: 4.3334. Min Range: -4.3334

Max Act: 4.3334. Min Act: -0.1700

Data Index: 4916737 (Open Web Text)

Max Activating Token Index: 872

Text #1

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.2829. Min Act: -0.1700

Data Index: 3678023 (Open Web Text)

Max Activating Token Index: 495

Text #2

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.2964. Min Act: -0.1700

Data Index: 5880896 (Open Web Text)

Max Activating Token Index: 762

Text #3

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.2767. Min Act: -0.1700

Data Index: 521970 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.3050. Min Act: -0.1700

Data Index: 1344535 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.2134. Min Act: -0.1700

Data Index: 413400 (Open Web Text)

Max Activating Token Index: 769

Text #6

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1881. Min Act: -0.1700

Data Index: 6448148 (Open Web Text)

Max Activating Token Index: 829

Text #7

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1804. Min Act: -0.1700

Data Index: 931500 (Open Web Text)

Max Activating Token Index: 274

Text #8

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1734. Min Act: -0.1700

Data Index: 6000702 (Open Web Text)

Max Activating Token Index: 901

Text #9

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1226. Min Act: -0.1700

Data Index: 73534 (Open Web Text)

Max Activating Token Index: 1001

Text #10

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1895. Min Act: -0.1700

Data Index: 1077049 (Open Web Text)

Max Activating Token Index: 355

Text #11

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0806. Min Act: -0.1700

Data Index: 2635021 (Open Web Text)

Max Activating Token Index: 756

Text #12

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1595. Min Act: -0.1700

Data Index: 7268860 (Open Web Text)

Max Activating Token Index: 276

Text #13

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.2216. Min Act: -0.1700

Data Index: 6795338 (Open Web Text)

Max Activating Token Index: 580

Text #14

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1195. Min Act: -0.1700

Data Index: 6583350 (Open Web Text)

Max Activating Token Index: 530

Text #15

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.0992. Min Act: -0.1700

Data Index: 825063 (Open Web Text)

Max Activating Token Index: 449

Text #16

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1380. Min Act: -0.1700

Data Index: 2332974 (Open Web Text)

Max Activating Token Index: 970

Text #17

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1106. Min Act: -0.1700

Data Index: 2278226 (Open Web Text)

Max Activating Token Index: 675

Text #18

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1786. Min Act: -0.1700

Data Index: 5865392 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 4.3334. Min Range: -4.3334

Max Act: 4.1158. Min Act: -0.1700

Data Index: 3674897 (Open Web Text)

Max Activating Token Index: 253