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

Dataset: Open Web Text

Neuron 1875 in Layer 3

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: 2.1991. Min Range: -2.1991

Max Act: 2.1873. Min Act: -0.1700

Data Index: 5896603 (Open Web Text)

Max Activating Token Index: 141

Text #1

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1974. Min Act: -0.1700

Data Index: 1899269 (Open Web Text)

Max Activating Token Index: 523

Text #2

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1991. Min Act: -0.1700

Data Index: 6822339 (Open Web Text)

Max Activating Token Index: 79

Text #3

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1767. Min Act: -0.1700

Data Index: 1703796 (Open Web Text)

Max Activating Token Index: 622

Text #4

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1803. Min Act: -0.1700

Data Index: 8388599 (Open Web Text)

Max Activating Token Index: 587

Text #5

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1662. Min Act: -0.1700

Data Index: 6502818 (Open Web Text)

Max Activating Token Index: 194

Text #6

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1772. Min Act: -0.1700

Data Index: 4050607 (Open Web Text)

Max Activating Token Index: 520

Text #7

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1820. Min Act: -0.1700

Data Index: 361820 (Open Web Text)

Max Activating Token Index: 284

Text #8

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1599. Min Act: -0.1700

Data Index: 2062971 (Open Web Text)

Max Activating Token Index: 1021

Text #9

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1485. Min Act: -0.1700

Data Index: 8734597 (Open Web Text)

Max Activating Token Index: 495

Text #10

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1453. Min Act: -0.1700

Data Index: 8433691 (Open Web Text)

Max Activating Token Index: 337

Text #11

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1654. Min Act: -0.1700

Data Index: 5987536 (Open Web Text)

Max Activating Token Index: 458

Text #12

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1358. Min Act: -0.1700

Data Index: 4632673 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1289. Min Act: -0.1700

Data Index: 4308255 (Open Web Text)

Max Activating Token Index: 142

Text #14

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1258. Min Act: -0.1700

Data Index: 4798885 (Open Web Text)

Max Activating Token Index: 552

Text #15

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1269. Min Act: -0.1700

Data Index: 267853 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1147. Min Act: -0.1700

Data Index: 5407689 (Open Web Text)

Max Activating Token Index: 850

Text #17

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1249. Min Act: -0.1700

Data Index: 5534365 (Open Web Text)

Max Activating Token Index: 935

Text #18

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1046. Min Act: -0.1700

Data Index: 4697724 (Open Web Text)

Max Activating Token Index: 831

Text #19

Max Range: 2.1991. Min Range: -2.1991

Max Act: 2.1105. Min Act: -0.1700

Data Index: 519579 (Open Web Text)

Max Activating Token Index: 358