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

Dataset: Open Web Text

Neuron 279 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: 4.7597. Min Range: -4.7597

Max Act: 4.7597. Min Act: -0.1700

Data Index: 52744 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.7213. Min Act: -0.1700

Data Index: 1358357 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.6633. Min Act: -0.1700

Data Index: 4652250 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.6418. Min Act: -0.1700

Data Index: 7177068 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.5871. Min Act: -0.1700

Data Index: 7818093 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.6079. Min Act: -0.1700

Data Index: 4210798 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.5762. Min Act: -0.1700

Data Index: 129465 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.5517. Min Act: -0.1700

Data Index: 1421203 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.5262. Min Act: -0.1700

Data Index: 6397180 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.4933. Min Act: -0.1700

Data Index: 3173832 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.5172. Min Act: -0.1700

Data Index: 6839113 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.4942. Min Act: -0.1700

Data Index: 7794309 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.5084. Min Act: -0.1700

Data Index: 7630217 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.4568. Min Act: -0.1700

Data Index: 3159158 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.4568. Min Act: -0.1700

Data Index: 2850222 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.4566. Min Act: -0.1700

Data Index: 962197 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.4332. Min Act: -0.1700

Data Index: 6350865 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.4503. Min Act: -0.1700

Data Index: 1893758 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.4262. Min Act: -0.1700

Data Index: 7115701 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.7597. Min Range: -4.7597

Max Act: 4.3949. Min Act: -0.1700

Data Index: 2142998 (Open Web Text)

Max Activating Token Index: 16