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

Dataset: Open Web Text

Neuron 2367 in Layer 4

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: 3.8369. Min Range: -3.8369

Max Act: 3.8369. Min Act: -0.1700

Data Index: 5774458 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.7201. Min Act: -0.1700

Data Index: 6696883 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6670. Min Act: -0.1700

Data Index: 5914192 (Open Web Text)

Max Activating Token Index: 514

Text #3

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6919. Min Act: -0.1700

Data Index: 3231544 (Open Web Text)

Max Activating Token Index: 965

Text #4

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6316. Min Act: -0.1700

Data Index: 4190202 (Open Web Text)

Max Activating Token Index: 70

Text #5

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6131. Min Act: -0.1700

Data Index: 7136113 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.6274. Min Act: -0.1700

Data Index: 2023085 (Open Web Text)

Max Activating Token Index: 954

Text #7

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5527. Min Act: -0.1700

Data Index: 2469409 (Open Web Text)

Max Activating Token Index: 829

Text #8

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5533. Min Act: -0.1700

Data Index: 6318639 (Open Web Text)

Max Activating Token Index: 771

Text #9

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5828. Min Act: -0.1700

Data Index: 7911103 (Open Web Text)

Max Activating Token Index: 739

Text #10

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5997. Min Act: -0.1700

Data Index: 1350379 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5334. Min Act: -0.1700

Data Index: 140240 (Open Web Text)

Max Activating Token Index: 239

Text #12

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5737. Min Act: -0.1700

Data Index: 509063 (Open Web Text)

Max Activating Token Index: 998

Text #13

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5422. Min Act: -0.1700

Data Index: 8302556 (Open Web Text)

Max Activating Token Index: 326

Text #14

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5446. Min Act: -0.1700

Data Index: 6597919 (Open Web Text)

Max Activating Token Index: 606

Text #15

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5492. Min Act: -0.1700

Data Index: 6591180 (Open Web Text)

Max Activating Token Index: 957

Text #16

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5384. Min Act: -0.1700

Data Index: 7900459 (Open Web Text)

Max Activating Token Index: 461

Text #17

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5126. Min Act: -0.1700

Data Index: 3182982 (Open Web Text)

Max Activating Token Index: 924

Text #18

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5358. Min Act: -0.1700

Data Index: 713591 (Open Web Text)

Max Activating Token Index: 415

Text #19

Max Range: 3.8369. Min Range: -3.8369

Max Act: 3.5297. Min Act: -0.1700

Data Index: 3147366 (Open Web Text)

Max Activating Token Index: 443