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

Dataset: Open Web Text

Neuron 391 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: 3.9216. Min Range: -3.9216

Max Act: 3.9216. Min Act: -0.1700

Data Index: 4546351 (Open Web Text)

Max Activating Token Index: 603

Text #1

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.8901. Min Act: -0.1700

Data Index: 3276442 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.8328. Min Act: -0.1700

Data Index: 1247559 (Open Web Text)

Max Activating Token Index: 735

Text #3

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.8211. Min Act: -0.1700

Data Index: 6417436 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7822. Min Act: -0.1700

Data Index: 3706918 (Open Web Text)

Max Activating Token Index: 906

Text #5

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7991. Min Act: -0.1700

Data Index: 2557948 (Open Web Text)

Max Activating Token Index: 61

Text #6

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7929. Min Act: -0.1700

Data Index: 1570933 (Open Web Text)

Max Activating Token Index: 236

Text #7

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7717. Min Act: -0.1700

Data Index: 4388287 (Open Web Text)

Max Activating Token Index: 517

Text #8

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7794. Min Act: -0.1700

Data Index: 6755605 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7890. Min Act: -0.1700

Data Index: 5136301 (Open Web Text)

Max Activating Token Index: 280

Text #10

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7665. Min Act: -0.1700

Data Index: 396453 (Open Web Text)

Max Activating Token Index: 199

Text #11

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7548. Min Act: -0.1700

Data Index: 2204744 (Open Web Text)

Max Activating Token Index: 629

Text #12

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7429. Min Act: -0.1700

Data Index: 8288190 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7649. Min Act: -0.1700

Data Index: 2210014 (Open Web Text)

Max Activating Token Index: 602

Text #14

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7469. Min Act: -0.1700

Data Index: 7449973 (Open Web Text)

Max Activating Token Index: 940

Text #15

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7315. Min Act: -0.1700

Data Index: 2186444 (Open Web Text)

Max Activating Token Index: 512

Text #16

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7515. Min Act: -0.1700

Data Index: 2553771 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7439. Min Act: -0.1700

Data Index: 1691728 (Open Web Text)

Max Activating Token Index: 738

Text #18

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7459. Min Act: -0.1700

Data Index: 6640332 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7325. Min Act: -0.1700

Data Index: 8039724 (Open Web Text)

Max Activating Token Index: 384