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

Dataset: Open Web Text

Neuron 1748 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: 1.8318. Min Range: -1.8318

Max Act: 1.8318. Min Act: -0.1700

Data Index: 7784474 (Open Web Text)

Max Activating Token Index: 802

Text #1

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.8309. Min Act: -0.1700

Data Index: 7779777 (Open Web Text)

Max Activating Token Index: 89

Text #2

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.8102. Min Act: -0.1700

Data Index: 4160872 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7963. Min Act: -0.1700

Data Index: 6689156 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7890. Min Act: -0.1700

Data Index: 3325252 (Open Web Text)

Max Activating Token Index: 956

Text #5

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7641. Min Act: -0.1700

Data Index: 6248367 (Open Web Text)

Max Activating Token Index: 354

Text #6

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7652. Min Act: -0.1700

Data Index: 2500940 (Open Web Text)

Max Activating Token Index: 868

Text #7

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7428. Min Act: -0.1700

Data Index: 1758601 (Open Web Text)

Max Activating Token Index: 650

Text #8

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7338. Min Act: -0.1700

Data Index: 7324463 (Open Web Text)

Max Activating Token Index: 324

Text #9

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7334. Min Act: -0.1700

Data Index: 3988088 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7217. Min Act: -0.1700

Data Index: 6833980 (Open Web Text)

Max Activating Token Index: 149

Text #11

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7074. Min Act: -0.1700

Data Index: 7309225 (Open Web Text)

Max Activating Token Index: 223

Text #12

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7194. Min Act: -0.1700

Data Index: 1770439 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7239. Min Act: -0.1700

Data Index: 6430758 (Open Web Text)

Max Activating Token Index: 861

Text #14

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7029. Min Act: -0.1700

Data Index: 7669500 (Open Web Text)

Max Activating Token Index: 77

Text #15

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.6953. Min Act: -0.1700

Data Index: 4250249 (Open Web Text)

Max Activating Token Index: 324

Text #16

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7030. Min Act: -0.1700

Data Index: 7709774 (Open Web Text)

Max Activating Token Index: 632

Text #17

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7054. Min Act: -0.1700

Data Index: 4454785 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.7051. Min Act: -0.1700

Data Index: 3658560 (Open Web Text)

Max Activating Token Index: 464

Text #19

Max Range: 1.8318. Min Range: -1.8318

Max Act: 1.6833. Min Act: -0.1700

Data Index: 6351940 (Open Web Text)

Max Activating Token Index: 240