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

Dataset: Open Web Text

Neuron 195 in Layer 3

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: 4.1104. Min Range: -4.1104

Max Act: 4.1104. Min Act: -0.1700

Data Index: 6961440 (Open Web Text)

Max Activating Token Index: 681

Text #1

Max Range: 4.1104. Min Range: -4.1104

Max Act: 4.0184. Min Act: -0.1700

Data Index: 4272417 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9608. Min Act: -0.1700

Data Index: 1516286 (Open Web Text)

Max Activating Token Index: 492

Text #3

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9377. Min Act: -0.1700

Data Index: 8267861 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9809. Min Act: -0.1700

Data Index: 4321191 (Open Web Text)

Max Activating Token Index: 555

Text #5

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9521. Min Act: -0.1700

Data Index: 2225438 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9317. Min Act: -0.1700

Data Index: 7283132 (Open Web Text)

Max Activating Token Index: 742

Text #7

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9445. Min Act: -0.1700

Data Index: 8566861 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9471. Min Act: -0.1700

Data Index: 797818 (Open Web Text)

Max Activating Token Index: 838

Text #9

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9341. Min Act: -0.1700

Data Index: 905108 (Open Web Text)

Max Activating Token Index: 71

Text #10

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9568. Min Act: -0.1700

Data Index: 3911913 (Open Web Text)

Max Activating Token Index: 262

Text #11

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9304. Min Act: -0.1700

Data Index: 7051745 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.8892. Min Act: -0.1700

Data Index: 7644714 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9092. Min Act: -0.1700

Data Index: 655717 (Open Web Text)

Max Activating Token Index: 94

Text #14

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9024. Min Act: -0.1700

Data Index: 5556872 (Open Web Text)

Max Activating Token Index: 634

Text #15

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9065. Min Act: -0.1700

Data Index: 952499 (Open Web Text)

Max Activating Token Index: 959

Text #16

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9409. Min Act: -0.1700

Data Index: 5018054 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9162. Min Act: -0.1700

Data Index: 887770 (Open Web Text)

Max Activating Token Index: 706

Text #18

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.8909. Min Act: -0.1700

Data Index: 4876685 (Open Web Text)

Max Activating Token Index: 578

Text #19

Max Range: 4.1104. Min Range: -4.1104

Max Act: 3.9315. Min Act: -0.1700

Data Index: 3164198 (Open Web Text)

Max Activating Token Index: 278