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

Dataset: Open Web Text

Neuron 974 in Layer 0

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: 3.6055. Min Range: -3.6055

Max Act: 3.6055. Min Act: -0.1700

Data Index: 4232095 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.6052. Min Act: -0.1700

Data Index: 2911742 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5733. Min Act: -0.1700

Data Index: 4364461 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5769. Min Act: -0.1700

Data Index: 1287367 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5762. Min Act: -0.1700

Data Index: 743573 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5801. Min Act: -0.1700

Data Index: 5814173 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5908. Min Act: -0.1700

Data Index: 4152605 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5588. Min Act: -0.1700

Data Index: 7156774 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5471. Min Act: -0.1700

Data Index: 2002407 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5528. Min Act: -0.1700

Data Index: 5073039 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5476. Min Act: -0.1700

Data Index: 8416710 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5547. Min Act: -0.1700

Data Index: 7897338 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5533. Min Act: -0.1700

Data Index: 7529197 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5504. Min Act: -0.1700

Data Index: 3375807 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5720. Min Act: -0.1700

Data Index: 7125573 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5378. Min Act: -0.1700

Data Index: 304548 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5493. Min Act: -0.1700

Data Index: 6675765 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5705. Min Act: -0.1700

Data Index: 1000406 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5428. Min Act: -0.1700

Data Index: 6654307 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5185. Min Act: -0.1700

Data Index: 1927645 (Open Web Text)

Max Activating Token Index: 6