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

Dataset: Open Web Text

Neuron 1789 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: 3.4210. Min Range: -3.4210

Max Act: 3.4210. Min Act: -0.1700

Data Index: 117780 (Open Web Text)

Max Activating Token Index: 985

Text #1

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.4164. Min Act: -0.1700

Data Index: 8171061 (Open Web Text)

Max Activating Token Index: 718

Text #2

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3730. Min Act: -0.1700

Data Index: 5775196 (Open Web Text)

Max Activating Token Index: 976

Text #3

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3560. Min Act: -0.1700

Data Index: 1948917 (Open Web Text)

Max Activating Token Index: 920

Text #4

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3384. Min Act: -0.1700

Data Index: 2941700 (Open Web Text)

Max Activating Token Index: 189

Text #5

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3677. Min Act: -0.1700

Data Index: 232666 (Open Web Text)

Max Activating Token Index: 1000

Text #6

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3261. Min Act: -0.1700

Data Index: 6947872 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3199. Min Act: -0.1700

Data Index: 5821836 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.3100. Min Act: -0.1700

Data Index: 5189506 (Open Web Text)

Max Activating Token Index: 809

Text #9

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2880. Min Act: -0.1700

Data Index: 8147473 (Open Web Text)

Max Activating Token Index: 962

Text #10

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2796. Min Act: -0.1700

Data Index: 4298449 (Open Web Text)

Max Activating Token Index: 136

Text #11

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2687. Min Act: -0.1700

Data Index: 5377954 (Open Web Text)

Max Activating Token Index: 803

Text #12

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2602. Min Act: -0.1700

Data Index: 4468809 (Open Web Text)

Max Activating Token Index: 740

Text #13

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2534. Min Act: -0.1700

Data Index: 3686953 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2378. Min Act: -0.1700

Data Index: 927579 (Open Web Text)

Max Activating Token Index: 939

Text #15

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2606. Min Act: -0.1700

Data Index: 567752 (Open Web Text)

Max Activating Token Index: 953

Text #16

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2355. Min Act: -0.1700

Data Index: 3061335 (Open Web Text)

Max Activating Token Index: 872

Text #17

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2598. Min Act: -0.1700

Data Index: 8165488 (Open Web Text)

Max Activating Token Index: 678

Text #18

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2248. Min Act: -0.1700

Data Index: 4233064 (Open Web Text)

Max Activating Token Index: 643

Text #19

Max Range: 3.4210. Min Range: -3.4210

Max Act: 3.2248. Min Act: -0.1700

Data Index: 8036110 (Open Web Text)

Max Activating Token Index: 815