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

Dataset: Open Web Text

Neuron 1505 in Layer 5

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: 2.7244. Min Range: -2.7244

Max Act: 2.7244. Min Act: -0.1699

Data Index: 4239963 (Open Web Text)

Max Activating Token Index: 325

Text #1

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.6918. Min Act: -0.1273

Data Index: 6415959 (Open Web Text)

Max Activating Token Index: 558

Text #2

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.6970. Min Act: -0.1700

Data Index: 720741 (Open Web Text)

Max Activating Token Index: 619

Text #3

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.6482. Min Act: -0.1131

Data Index: 8082683 (Open Web Text)

Max Activating Token Index: 896

Text #4

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.6413. Min Act: -0.1700

Data Index: 3309025 (Open Web Text)

Max Activating Token Index: 789

Text #5

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.6583. Min Act: -0.1700

Data Index: 6553873 (Open Web Text)

Max Activating Token Index: 1016

Text #6

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.6275. Min Act: -0.1700

Data Index: 7621560 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.6361. Min Act: -0.1698

Data Index: 3823083 (Open Web Text)

Max Activating Token Index: 484

Text #8

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.6034. Min Act: -0.1700

Data Index: 720745 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5746. Min Act: -0.1529

Data Index: 8082684 (Open Web Text)

Max Activating Token Index: 334

Text #10

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5672. Min Act: -0.1684

Data Index: 4798327 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5723. Min Act: -0.1690

Data Index: 3958621 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5564. Min Act: -0.1676

Data Index: 6333855 (Open Web Text)

Max Activating Token Index: 632

Text #13

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5599. Min Act: -0.1557

Data Index: 4798326 (Open Web Text)

Max Activating Token Index: 534

Text #14

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5608. Min Act: -0.1696

Data Index: 7271311 (Open Web Text)

Max Activating Token Index: 560

Text #15

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5735. Min Act: -0.1700

Data Index: 5634769 (Open Web Text)

Max Activating Token Index: 1006

Text #16

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5333. Min Act: -0.1700

Data Index: 7181559 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5424. Min Act: -0.1672

Data Index: 3914323 (Open Web Text)

Max Activating Token Index: 623

Text #18

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5469. Min Act: -0.1700

Data Index: 7181557 (Open Web Text)

Max Activating Token Index: 775

Text #19

Max Range: 2.7244. Min Range: -2.7244

Max Act: 2.5602. Min Act: -0.1700

Data Index: 2268767 (Open Web Text)

Max Activating Token Index: 687