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

Dataset: Open Web Text

Neuron 700 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: 3.5103. Min Range: -3.5103

Max Act: 3.5103. Min Act: -0.1700

Data Index: 7108538 (Open Web Text)

Max Activating Token Index: 414

Text #1

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4587. Min Act: -0.1700

Data Index: 3889528 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4865. Min Act: -0.1700

Data Index: 6757661 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4566. Min Act: -0.1700

Data Index: 8477731 (Open Web Text)

Max Activating Token Index: 338

Text #4

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4264. Min Act: -0.1700

Data Index: 246300 (Open Web Text)

Max Activating Token Index: 520

Text #5

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4245. Min Act: -0.1700

Data Index: 8129413 (Open Web Text)

Max Activating Token Index: 941

Text #6

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4441. Min Act: -0.1700

Data Index: 6323504 (Open Web Text)

Max Activating Token Index: 735

Text #7

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4492. Min Act: -0.1700

Data Index: 4672781 (Open Web Text)

Max Activating Token Index: 401

Text #8

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4258. Min Act: -0.1700

Data Index: 5837654 (Open Web Text)

Max Activating Token Index: 937

Text #9

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4246. Min Act: -0.1700

Data Index: 6358241 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4036. Min Act: -0.1700

Data Index: 8541119 (Open Web Text)

Max Activating Token Index: 725

Text #11

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4282. Min Act: -0.1700

Data Index: 5945312 (Open Web Text)

Max Activating Token Index: 771

Text #12

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3957. Min Act: -0.1700

Data Index: 2198024 (Open Web Text)

Max Activating Token Index: 399

Text #13

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4078. Min Act: -0.1700

Data Index: 4020581 (Open Web Text)

Max Activating Token Index: 316

Text #14

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3795. Min Act: -0.1700

Data Index: 7574661 (Open Web Text)

Max Activating Token Index: 554

Text #15

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3775. Min Act: -0.1700

Data Index: 6765121 (Open Web Text)

Max Activating Token Index: 361

Text #16

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4100. Min Act: -0.1700

Data Index: 7331562 (Open Web Text)

Max Activating Token Index: 483

Text #17

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3849. Min Act: -0.1700

Data Index: 7803978 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3897. Min Act: -0.1700

Data Index: 6450503 (Open Web Text)

Max Activating Token Index: 503

Text #19

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3690. Min Act: -0.1700

Data Index: 6476396 (Open Web Text)

Max Activating Token Index: 660