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

Dataset: Open Web Text

Neuron 2821 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: 4.9408. Min Range: -4.9408

Max Act: 4.9152. Min Act: -0.1700

Data Index: 1087413 (Open Web Text)

Max Activating Token Index: 286

Text #1

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.9408. Min Act: -0.1700

Data Index: 8368082 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8935. Min Act: -0.1700

Data Index: 8609710 (Open Web Text)

Max Activating Token Index: 557

Text #3

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.9065. Min Act: -0.1700

Data Index: 4508760 (Open Web Text)

Max Activating Token Index: 641

Text #4

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8631. Min Act: -0.1700

Data Index: 209915 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8718. Min Act: -0.1700

Data Index: 2690160 (Open Web Text)

Max Activating Token Index: 119

Text #6

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8767. Min Act: -0.1700

Data Index: 2390414 (Open Web Text)

Max Activating Token Index: 520

Text #7

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8863. Min Act: -0.1700

Data Index: 6133788 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8640. Min Act: -0.1700

Data Index: 4226213 (Open Web Text)

Max Activating Token Index: 767

Text #9

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8552. Min Act: -0.1700

Data Index: 2954725 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8463. Min Act: -0.1700

Data Index: 3603368 (Open Web Text)

Max Activating Token Index: 425

Text #11

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.7819. Min Act: -0.1700

Data Index: 40444 (Open Web Text)

Max Activating Token Index: 612

Text #12

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8347. Min Act: -0.1700

Data Index: 2025264 (Open Web Text)

Max Activating Token Index: 287

Text #13

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8131. Min Act: -0.1700

Data Index: 4778351 (Open Web Text)

Max Activating Token Index: 213

Text #14

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.7973. Min Act: -0.1700

Data Index: 7248018 (Open Web Text)

Max Activating Token Index: 284

Text #15

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8274. Min Act: -0.1700

Data Index: 298498 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8246. Min Act: -0.1700

Data Index: 3563018 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.8127. Min Act: -0.1700

Data Index: 7285568 (Open Web Text)

Max Activating Token Index: 733

Text #18

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.7978. Min Act: -0.1700

Data Index: 8171943 (Open Web Text)

Max Activating Token Index: 526

Text #19

Max Range: 4.9408. Min Range: -4.9408

Max Act: 4.7763. Min Act: -0.1700

Data Index: 4746574 (Open Web Text)

Max Activating Token Index: 53