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

Dataset: Open Web Text

Neuron 1107 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: 1.9970. Min Range: -1.9970

Max Act: 1.9970. Min Act: -0.1700

Data Index: 3519437 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.8903. Min Act: -0.1700

Data Index: 7449139 (Open Web Text)

Max Activating Token Index: 620

Text #2

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.8576. Min Act: -0.1700

Data Index: 2766924 (Open Web Text)

Max Activating Token Index: 479

Text #3

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.8358. Min Act: -0.1700

Data Index: 4150000 (Open Web Text)

Max Activating Token Index: 1012

Text #4

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.8379. Min Act: -0.1700

Data Index: 5660866 (Open Web Text)

Max Activating Token Index: 700

Text #5

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.8291. Min Act: -0.1700

Data Index: 7585890 (Open Web Text)

Max Activating Token Index: 503

Text #6

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.8386. Min Act: -0.1700

Data Index: 1304647 (Open Web Text)

Max Activating Token Index: 203

Text #7

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.8209. Min Act: -0.1700

Data Index: 1399423 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.8003. Min Act: -0.1700

Data Index: 4900524 (Open Web Text)

Max Activating Token Index: 553

Text #9

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7941. Min Act: -0.1700

Data Index: 7910262 (Open Web Text)

Max Activating Token Index: 237

Text #10

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7983. Min Act: -0.1700

Data Index: 70058 (Open Web Text)

Max Activating Token Index: 500

Text #11

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7963. Min Act: -0.1700

Data Index: 1096006 (Open Web Text)

Max Activating Token Index: 407

Text #12

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7935. Min Act: -0.1700

Data Index: 393510 (Open Web Text)

Max Activating Token Index: 685

Text #13

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7795. Min Act: -0.1700

Data Index: 2978100 (Open Web Text)

Max Activating Token Index: 703

Text #14

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7739. Min Act: -0.1700

Data Index: 4238955 (Open Web Text)

Max Activating Token Index: 656

Text #15

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7621. Min Act: -0.1700

Data Index: 809982 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7783. Min Act: -0.1700

Data Index: 2917492 (Open Web Text)

Max Activating Token Index: 294

Text #17

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7730. Min Act: -0.1700

Data Index: 3216603 (Open Web Text)

Max Activating Token Index: 144

Text #18

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7594. Min Act: -0.1700

Data Index: 1096014 (Open Web Text)

Max Activating Token Index: 782

Text #19

Max Range: 1.9970. Min Range: -1.9970

Max Act: 1.7688. Min Act: -0.1700

Data Index: 4565133 (Open Web Text)

Max Activating Token Index: 928