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

Dataset: Open Web Text

Neuron 1016 in Layer 0

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: 7.1629. Min Range: -7.1629

Max Act: 7.1629. Min Act: -0.1700

Data Index: 5898971 (Open Web Text)

Max Activating Token Index: 864

Text #1

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0968. Min Act: -0.1700

Data Index: 2730430 (Open Web Text)

Max Activating Token Index: 566

Text #2

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.1336. Min Act: -0.1700

Data Index: 3601201 (Open Web Text)

Max Activating Token Index: 198

Text #3

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0899. Min Act: -0.1700

Data Index: 2255375 (Open Web Text)

Max Activating Token Index: 598

Text #4

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0904. Min Act: -0.1700

Data Index: 157348 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0936. Min Act: -0.1700

Data Index: 1609555 (Open Web Text)

Max Activating Token Index: 647

Text #6

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0455. Min Act: -0.1700

Data Index: 7945577 (Open Web Text)

Max Activating Token Index: 639

Text #7

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0314. Min Act: -0.1700

Data Index: 3252392 (Open Web Text)

Max Activating Token Index: 821

Text #8

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0038. Min Act: -0.1700

Data Index: 372518 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0334. Min Act: -0.1700

Data Index: 2013098 (Open Web Text)

Max Activating Token Index: 179

Text #10

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0090. Min Act: -0.1700

Data Index: 6984030 (Open Web Text)

Max Activating Token Index: 213

Text #11

Max Range: 7.1629. Min Range: -7.1629

Max Act: 6.9742. Min Act: -0.1700

Data Index: 3146736 (Open Web Text)

Max Activating Token Index: 563

Text #12

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0009. Min Act: -0.1700

Data Index: 5422025 (Open Web Text)

Max Activating Token Index: 672

Text #13

Max Range: 7.1629. Min Range: -7.1629

Max Act: 7.0190. Min Act: -0.1700

Data Index: 6075395 (Open Web Text)

Max Activating Token Index: 724

Text #14

Max Range: 7.1629. Min Range: -7.1629

Max Act: 6.9513. Min Act: -0.1700

Data Index: 6581441 (Open Web Text)

Max Activating Token Index: 317

Text #15

Max Range: 7.1629. Min Range: -7.1629

Max Act: 6.9961. Min Act: -0.1700

Data Index: 4727786 (Open Web Text)

Max Activating Token Index: 392

Text #16

Max Range: 7.1629. Min Range: -7.1629

Max Act: 6.9485. Min Act: -0.1700

Data Index: 5491445 (Open Web Text)

Max Activating Token Index: 754

Text #17

Max Range: 7.1629. Min Range: -7.1629

Max Act: 6.9515. Min Act: -0.1700

Data Index: 8564036 (Open Web Text)

Max Activating Token Index: 471

Text #18

Max Range: 7.1629. Min Range: -7.1629

Max Act: 6.9554. Min Act: -0.1700

Data Index: 1068644 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 7.1629. Min Range: -7.1629

Max Act: 6.9239. Min Act: -0.1700

Data Index: 824077 (Open Web Text)

Max Activating Token Index: 671