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

Dataset: Open Web Text

Neuron 1860 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: 6.2046. Min Range: -6.2046

Max Act: 6.2046. Min Act: -0.1700

Data Index: 3957238 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 6.2046. Min Range: -6.2046

Max Act: 6.0140. Min Act: -0.1700

Data Index: 7401930 (Open Web Text)

Max Activating Token Index: 345

Text #2

Max Range: 6.2046. Min Range: -6.2046

Max Act: 6.0183. Min Act: -0.1700

Data Index: 1197794 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 6.2046. Min Range: -6.2046

Max Act: 6.0292. Min Act: -0.1700

Data Index: 4542753 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.9610. Min Act: -0.1700

Data Index: 5035631 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.8997. Min Act: -0.1700

Data Index: 178054 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.8445. Min Act: -0.1700

Data Index: 4642798 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.7872. Min Act: -0.1700

Data Index: 4813151 (Open Web Text)

Max Activating Token Index: 49

Text #8

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.7788. Min Act: -0.1700

Data Index: 6625548 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.8216. Min Act: -0.1700

Data Index: 5415391 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.7990. Min Act: -0.1700

Data Index: 3633470 (Open Web Text)

Max Activating Token Index: 68

Text #11

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.7842. Min Act: -0.1700

Data Index: 8107571 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.7611. Min Act: -0.1700

Data Index: 6989453 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.7048. Min Act: -0.1700

Data Index: 438983 (Open Web Text)

Max Activating Token Index: 752

Text #14

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.7433. Min Act: -0.1700

Data Index: 934756 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.6980. Min Act: -0.1700

Data Index: 1005403 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.6765. Min Act: -0.1700

Data Index: 3060294 (Open Web Text)

Max Activating Token Index: 689

Text #17

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.6977. Min Act: -0.1700

Data Index: 698545 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.7070. Min Act: -0.1700

Data Index: 6054008 (Open Web Text)

Max Activating Token Index: 668

Text #19

Max Range: 6.2046. Min Range: -6.2046

Max Act: 5.7042. Min Act: -0.1700

Data Index: 4548874 (Open Web Text)

Max Activating Token Index: 23