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

Dataset: Open Web Text

Neuron 1100 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: 3.6811. Min Range: -3.6811

Max Act: 3.6811. Min Act: -0.1700

Data Index: 7624184 (Open Web Text)

Max Activating Token Index: 477

Text #1

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6736. Min Act: -0.1700

Data Index: 6477996 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6486. Min Act: -0.1700

Data Index: 8122172 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6447. Min Act: -0.1700

Data Index: 1816170 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6304. Min Act: -0.1700

Data Index: 4956363 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6403. Min Act: -0.1700

Data Index: 1857460 (Open Web Text)

Max Activating Token Index: 32

Text #6

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6542. Min Act: -0.1700

Data Index: 3832189 (Open Web Text)

Max Activating Token Index: 852

Text #7

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6140. Min Act: -0.1700

Data Index: 2380077 (Open Web Text)

Max Activating Token Index: 700

Text #8

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6638. Min Act: -0.1700

Data Index: 4712915 (Open Web Text)

Max Activating Token Index: 558

Text #9

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6257. Min Act: -0.1700

Data Index: 5496166 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6320. Min Act: -0.1700

Data Index: 6647431 (Open Web Text)

Max Activating Token Index: 678

Text #11

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.6335. Min Act: -0.1700

Data Index: 1001948 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.5845. Min Act: -0.1700

Data Index: 6076977 (Open Web Text)

Max Activating Token Index: 604

Text #13

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.5784. Min Act: -0.1700

Data Index: 849380 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.5881. Min Act: -0.1700

Data Index: 7116334 (Open Web Text)

Max Activating Token Index: 847

Text #15

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.5973. Min Act: -0.1700

Data Index: 3860317 (Open Web Text)

Max Activating Token Index: 932

Text #16

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.5999. Min Act: -0.1700

Data Index: 2237165 (Open Web Text)

Max Activating Token Index: 349

Text #17

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.5562. Min Act: -0.1700

Data Index: 7946341 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.5890. Min Act: -0.1700

Data Index: 2795054 (Open Web Text)

Max Activating Token Index: 492

Text #19

Max Range: 3.6811. Min Range: -3.6811

Max Act: 3.5445. Min Act: -0.1700

Data Index: 240624 (Open Web Text)

Max Activating Token Index: 616