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

Dataset: Open Web Text

Neuron 1408 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: 3.5035. Min Range: -3.5035

Max Act: 3.5035. Min Act: -0.1700

Data Index: 3139255 (Open Web Text)

Max Activating Token Index: 87

Text #1

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.4517. Min Act: -0.1700

Data Index: 1992906 (Open Web Text)

Max Activating Token Index: 951

Text #2

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.4384. Min Act: -0.1700

Data Index: 689113 (Open Web Text)

Max Activating Token Index: 45

Text #3

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.4431. Min Act: -0.1700

Data Index: 5414631 (Open Web Text)

Max Activating Token Index: 199

Text #4

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.4006. Min Act: -0.1700

Data Index: 8762058 (Open Web Text)

Max Activating Token Index: 918

Text #5

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3942. Min Act: -0.1700

Data Index: 4303432 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3783. Min Act: -0.1700

Data Index: 1718323 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3865. Min Act: -0.1700

Data Index: 6866820 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3652. Min Act: -0.1700

Data Index: 3232936 (Open Web Text)

Max Activating Token Index: 985

Text #9

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3555. Min Act: -0.1700

Data Index: 2484053 (Open Web Text)

Max Activating Token Index: 716

Text #10

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3536. Min Act: -0.1700

Data Index: 277696 (Open Web Text)

Max Activating Token Index: 123

Text #11

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3832. Min Act: -0.1700

Data Index: 8485492 (Open Web Text)

Max Activating Token Index: 978

Text #12

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3377. Min Act: -0.1700

Data Index: 4154175 (Open Web Text)

Max Activating Token Index: 611

Text #13

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3657. Min Act: -0.1700

Data Index: 277693 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3435. Min Act: -0.1700

Data Index: 1720341 (Open Web Text)

Max Activating Token Index: 555

Text #15

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3279. Min Act: -0.1700

Data Index: 1415855 (Open Web Text)

Max Activating Token Index: 171

Text #16

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3265. Min Act: -0.1700

Data Index: 3444001 (Open Web Text)

Max Activating Token Index: 946

Text #17

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3309. Min Act: -0.1700

Data Index: 978817 (Open Web Text)

Max Activating Token Index: 113

Text #18

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3474. Min Act: -0.1700

Data Index: 1442685 (Open Web Text)

Max Activating Token Index: 674

Text #19

Max Range: 3.5035. Min Range: -3.5035

Max Act: 3.3471. Min Act: -0.1700

Data Index: 7255996 (Open Web Text)

Max Activating Token Index: 207