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

Dataset: Open Web Text

Neuron 2842 in Layer 1

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: 1.4944. Min Range: -1.4944

Max Act: 1.4944. Min Act: -0.1700

Data Index: 5891072 (Open Web Text)

Max Activating Token Index: 777

Text #1

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.4505. Min Act: -0.1700

Data Index: 1158008 (Open Web Text)

Max Activating Token Index: 264

Text #2

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.4268. Min Act: -0.1700

Data Index: 2276698 (Open Web Text)

Max Activating Token Index: 796

Text #3

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.4164. Min Act: -0.1700

Data Index: 4419309 (Open Web Text)

Max Activating Token Index: 518

Text #4

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3964. Min Act: -0.1700

Data Index: 6139381 (Open Web Text)

Max Activating Token Index: 979

Text #5

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3926. Min Act: -0.1700

Data Index: 4178489 (Open Web Text)

Max Activating Token Index: 130

Text #6

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3861. Min Act: -0.1700

Data Index: 4174809 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3986. Min Act: -0.1700

Data Index: 5760992 (Open Web Text)

Max Activating Token Index: 1003

Text #8

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3875. Min Act: -0.1700

Data Index: 2144880 (Open Web Text)

Max Activating Token Index: 739

Text #9

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3805. Min Act: -0.1700

Data Index: 3845863 (Open Web Text)

Max Activating Token Index: 83

Text #10

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3807. Min Act: -0.1700

Data Index: 4444526 (Open Web Text)

Max Activating Token Index: 254

Text #11

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3663. Min Act: -0.1700

Data Index: 4490394 (Open Web Text)

Max Activating Token Index: 900

Text #12

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3666. Min Act: -0.1700

Data Index: 173985 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3411. Min Act: -0.1700

Data Index: 6488965 (Open Web Text)

Max Activating Token Index: 993

Text #14

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3587. Min Act: -0.1700

Data Index: 5688370 (Open Web Text)

Max Activating Token Index: 903

Text #15

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3634. Min Act: -0.1700

Data Index: 5456121 (Open Web Text)

Max Activating Token Index: 950

Text #16

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3649. Min Act: -0.1700

Data Index: 5149360 (Open Web Text)

Max Activating Token Index: 760

Text #17

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3703. Min Act: -0.1700

Data Index: 4866781 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3481. Min Act: -0.1700

Data Index: 3237463 (Open Web Text)

Max Activating Token Index: 918

Text #19

Max Range: 1.4944. Min Range: -1.4944

Max Act: 1.3531. Min Act: -0.1700

Data Index: 1133350 (Open Web Text)

Max Activating Token Index: 582