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

Dataset: Open Web Text

Neuron 3014 in Layer 4

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: 4.2926. Min Range: -4.2926

Max Act: 4.2926. Min Act: -0.1700

Data Index: 5153012 (Open Web Text)

Max Activating Token Index: 158

Text #1

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.2207. Min Act: -0.1700

Data Index: 1299853 (Open Web Text)

Max Activating Token Index: 295

Text #2

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.2370. Min Act: -0.1700

Data Index: 6708185 (Open Web Text)

Max Activating Token Index: 971

Text #3

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.1644. Min Act: -0.1700

Data Index: 1418718 (Open Web Text)

Max Activating Token Index: 955

Text #4

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.1261. Min Act: -0.1700

Data Index: 1033349 (Open Web Text)

Max Activating Token Index: 627

Text #5

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.1131. Min Act: -0.1700

Data Index: 7413677 (Open Web Text)

Max Activating Token Index: 782

Text #6

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.1194. Min Act: -0.1700

Data Index: 5317847 (Open Web Text)

Max Activating Token Index: 953

Text #7

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0706. Min Act: -0.1700

Data Index: 434207 (Open Web Text)

Max Activating Token Index: 110

Text #8

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0691. Min Act: -0.1700

Data Index: 8709490 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0798. Min Act: -0.1700

Data Index: 2613180 (Open Web Text)

Max Activating Token Index: 495

Text #10

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0113. Min Act: -0.1700

Data Index: 4290010 (Open Web Text)

Max Activating Token Index: 990

Text #11

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0390. Min Act: -0.1700

Data Index: 166428 (Open Web Text)

Max Activating Token Index: 319

Text #12

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0270. Min Act: -0.1700

Data Index: 5741528 (Open Web Text)

Max Activating Token Index: 473

Text #13

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0739. Min Act: -0.1700

Data Index: 4920908 (Open Web Text)

Max Activating Token Index: 288

Text #14

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0322. Min Act: -0.1700

Data Index: 3819681 (Open Web Text)

Max Activating Token Index: 591

Text #15

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0175. Min Act: -0.1700

Data Index: 8000046 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 4.2926. Min Range: -4.2926

Max Act: 3.9907. Min Act: -0.1700

Data Index: 5675701 (Open Web Text)

Max Activating Token Index: 519

Text #17

Max Range: 4.2926. Min Range: -4.2926

Max Act: 3.9831. Min Act: -0.1700

Data Index: 3665 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0194. Min Act: -0.1700

Data Index: 272734 (Open Web Text)

Max Activating Token Index: 367

Text #19

Max Range: 4.2926. Min Range: -4.2926

Max Act: 4.0135. Min Act: -0.1700

Data Index: 3635722 (Open Web Text)

Max Activating Token Index: 100