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

Dataset: Open Web Text

Neuron 1032 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: 4.4214. Min Range: -4.4214

Max Act: 4.4214. Min Act: -0.1700

Data Index: 3851645 (Open Web Text)

Max Activating Token Index: 23

Text #1

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3743. Min Act: -0.1700

Data Index: 2926969 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3750. Min Act: -0.1700

Data Index: 1600148 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3577. Min Act: -0.1700

Data Index: 1450852 (Open Web Text)

Max Activating Token Index: 253

Text #4

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3609. Min Act: -0.1700

Data Index: 6364937 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3284. Min Act: -0.1700

Data Index: 6873776 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3117. Min Act: -0.1700

Data Index: 6848815 (Open Web Text)

Max Activating Token Index: 820

Text #7

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3317. Min Act: -0.1700

Data Index: 1126545 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3175. Min Act: -0.1700

Data Index: 8612256 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3179. Min Act: -0.1700

Data Index: 7808011 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.2802. Min Act: -0.1700

Data Index: 5443312 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3049. Min Act: -0.1700

Data Index: 6008906 (Open Web Text)

Max Activating Token Index: 866

Text #12

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.3191. Min Act: -0.1700

Data Index: 6119096 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.2930. Min Act: -0.1700

Data Index: 798641 (Open Web Text)

Max Activating Token Index: 27

Text #14

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.2885. Min Act: -0.1700

Data Index: 3533424 (Open Web Text)

Max Activating Token Index: 676

Text #15

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.2932. Min Act: -0.1700

Data Index: 2111126 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.2795. Min Act: -0.1700

Data Index: 1662995 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.2910. Min Act: -0.1700

Data Index: 159929 (Open Web Text)

Max Activating Token Index: 126

Text #18

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.2998. Min Act: -0.1700

Data Index: 6525030 (Open Web Text)

Max Activating Token Index: 44

Text #19

Max Range: 4.4214. Min Range: -4.4214

Max Act: 4.2729. Min Act: -0.1700

Data Index: 4066179 (Open Web Text)

Max Activating Token Index: 499