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

Dataset: Open Web Text

Neuron 1847 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: 2.9767. Min Range: -2.9767

Max Act: 2.9746. Min Act: -0.1700

Data Index: 4651944 (Open Web Text)

Max Activating Token Index: 646

Text #1

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9767. Min Act: -0.1700

Data Index: 5577849 (Open Web Text)

Max Activating Token Index: 93

Text #2

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9182. Min Act: -0.1700

Data Index: 8067901 (Open Web Text)

Max Activating Token Index: 151

Text #3

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9288. Min Act: -0.1700

Data Index: 1028041 (Open Web Text)

Max Activating Token Index: 994

Text #4

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9366. Min Act: -0.1700

Data Index: 6520225 (Open Web Text)

Max Activating Token Index: 996

Text #5

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9385. Min Act: -0.1700

Data Index: 1011792 (Open Web Text)

Max Activating Token Index: 858

Text #6

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9206. Min Act: -0.1700

Data Index: 2177048 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9318. Min Act: -0.1700

Data Index: 5384951 (Open Web Text)

Max Activating Token Index: 318

Text #8

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9124. Min Act: -0.1700

Data Index: 1604451 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9082. Min Act: -0.1700

Data Index: 2112336 (Open Web Text)

Max Activating Token Index: 861

Text #10

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9154. Min Act: -0.1700

Data Index: 2240426 (Open Web Text)

Max Activating Token Index: 934

Text #11

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9111. Min Act: -0.1700

Data Index: 2553622 (Open Web Text)

Max Activating Token Index: 837

Text #12

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9078. Min Act: -0.1700

Data Index: 6890808 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.8872. Min Act: -0.1700

Data Index: 5012007 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9093. Min Act: -0.1700

Data Index: 267536 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.8904. Min Act: -0.1700

Data Index: 8591901 (Open Web Text)

Max Activating Token Index: 285

Text #16

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9003. Min Act: -0.1700

Data Index: 4714502 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9007. Min Act: -0.1700

Data Index: 4307196 (Open Web Text)

Max Activating Token Index: 411

Text #18

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.9069. Min Act: -0.1700

Data Index: 5957920 (Open Web Text)

Max Activating Token Index: 935

Text #19

Max Range: 2.9767. Min Range: -2.9767

Max Act: 2.8916. Min Act: -0.1700

Data Index: 4650420 (Open Web Text)

Max Activating Token Index: 190