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

Dataset: Open Web Text

Neuron 395 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: 4.1182. Min Range: -4.1182

Max Act: 4.1161. Min Act: -0.1700

Data Index: 2145782 (Open Web Text)

Max Activating Token Index: 294

Text #1

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.1182. Min Act: -0.1700

Data Index: 2768168 (Open Web Text)

Max Activating Token Index: 760

Text #2

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.1140. Min Act: -0.1700

Data Index: 2206165 (Open Web Text)

Max Activating Token Index: 626

Text #3

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0940. Min Act: -0.1700

Data Index: 1049565 (Open Web Text)

Max Activating Token Index: 546

Text #4

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0588. Min Act: -0.1700

Data Index: 7253546 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0278. Min Act: -0.1700

Data Index: 2366594 (Open Web Text)

Max Activating Token Index: 536

Text #6

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0290. Min Act: -0.1700

Data Index: 1330733 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0422. Min Act: -0.1700

Data Index: 767325 (Open Web Text)

Max Activating Token Index: 511

Text #8

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0021. Min Act: -0.1700

Data Index: 8789840 (Open Web Text)

Max Activating Token Index: 74

Text #9

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0311. Min Act: -0.1700

Data Index: 295438 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 4.1182. Min Range: -4.1182

Max Act: 3.9949. Min Act: -0.1700

Data Index: 4085668 (Open Web Text)

Max Activating Token Index: 474

Text #11

Max Range: 4.1182. Min Range: -4.1182

Max Act: 3.9998. Min Act: -0.1700

Data Index: 4749616 (Open Web Text)

Max Activating Token Index: 566

Text #12

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0255. Min Act: -0.1700

Data Index: 5363600 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 4.1182. Min Range: -4.1182

Max Act: 3.9982. Min Act: -0.1700

Data Index: 1503968 (Open Web Text)

Max Activating Token Index: 756

Text #14

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0259. Min Act: -0.1700

Data Index: 2998713 (Open Web Text)

Max Activating Token Index: 258

Text #15

Max Range: 4.1182. Min Range: -4.1182

Max Act: 4.0079. Min Act: -0.1700

Data Index: 1275327 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.1182. Min Range: -4.1182

Max Act: 3.9875. Min Act: -0.1700

Data Index: 885452 (Open Web Text)

Max Activating Token Index: 585

Text #17

Max Range: 4.1182. Min Range: -4.1182

Max Act: 3.9707. Min Act: -0.1700

Data Index: 2968719 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.1182. Min Range: -4.1182

Max Act: 3.9768. Min Act: -0.1700

Data Index: 6820855 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 4.1182. Min Range: -4.1182

Max Act: 3.9712. Min Act: -0.1700

Data Index: 3351034 (Open Web Text)

Max Activating Token Index: 543