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

Dataset: Open Web Text

Neuron 2063 in Layer 6

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: 5.1504. Min Range: -5.1504

Max Act: 5.1504. Min Act: -0.1700

Data Index: 1660101 (Open Web Text)

Max Activating Token Index: 714

Text #1

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.0917. Min Act: -0.1700

Data Index: 1997605 (Open Web Text)

Max Activating Token Index: 743

Text #2

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.0746. Min Act: -0.1700

Data Index: 7105060 (Open Web Text)

Max Activating Token Index: 911

Text #3

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.1032. Min Act: -0.1700

Data Index: 111073 (Open Web Text)

Max Activating Token Index: 935

Text #4

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.0773. Min Act: -0.1700

Data Index: 7531920 (Open Web Text)

Max Activating Token Index: 563

Text #5

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.0735. Min Act: -0.1700

Data Index: 5615477 (Open Web Text)

Max Activating Token Index: 113

Text #6

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.0767. Min Act: -0.1700

Data Index: 4056512 (Open Web Text)

Max Activating Token Index: 965

Text #7

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.0041. Min Act: -0.1700

Data Index: 5717068 (Open Web Text)

Max Activating Token Index: 454

Text #8

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9649. Min Act: -0.1700

Data Index: 7670808 (Open Web Text)

Max Activating Token Index: 639

Text #9

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9960. Min Act: -0.1700

Data Index: 7389256 (Open Web Text)

Max Activating Token Index: 41

Text #10

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.0174. Min Act: -0.1700

Data Index: 1817537 (Open Web Text)

Max Activating Token Index: 192

Text #11

Max Range: 5.1504. Min Range: -5.1504

Max Act: 5.0022. Min Act: -0.1700

Data Index: 1406556 (Open Web Text)

Max Activating Token Index: 201

Text #12

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9786. Min Act: -0.1700

Data Index: 757161 (Open Web Text)

Max Activating Token Index: 450

Text #13

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9708. Min Act: -0.1700

Data Index: 7779883 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9868. Min Act: -0.1700

Data Index: 986321 (Open Web Text)

Max Activating Token Index: 903

Text #15

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9858. Min Act: -0.1700

Data Index: 2210146 (Open Web Text)

Max Activating Token Index: 383

Text #16

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9614. Min Act: -0.1700

Data Index: 7814271 (Open Web Text)

Max Activating Token Index: 93

Text #17

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9795. Min Act: -0.1700

Data Index: 1632472 (Open Web Text)

Max Activating Token Index: 799

Text #18

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9608. Min Act: -0.1700

Data Index: 5109317 (Open Web Text)

Max Activating Token Index: 536

Text #19

Max Range: 5.1504. Min Range: -5.1504

Max Act: 4.9302. Min Act: -0.1700

Data Index: 5026603 (Open Web Text)

Max Activating Token Index: 400