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

Dataset: Open Web Text

Neuron 80 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: 1.9472. Min Range: -1.9472

Max Act: 1.9472. Min Act: -0.1700

Data Index: 6497092 (Open Web Text)

Max Activating Token Index: 93

Text #1

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.9336. Min Act: -0.1700

Data Index: 1698802 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.9048. Min Act: -0.1700

Data Index: 5499927 (Open Web Text)

Max Activating Token Index: 621

Text #3

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.9006. Min Act: -0.1700

Data Index: 5453700 (Open Web Text)

Max Activating Token Index: 546

Text #4

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.9029. Min Act: -0.1700

Data Index: 6028856 (Open Web Text)

Max Activating Token Index: 343

Text #5

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8932. Min Act: -0.1700

Data Index: 847191 (Open Web Text)

Max Activating Token Index: 762

Text #6

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8949. Min Act: -0.1700

Data Index: 1264700 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8882. Min Act: -0.1700

Data Index: 20040 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8753. Min Act: -0.1700

Data Index: 7393514 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8806. Min Act: -0.1700

Data Index: 4803206 (Open Web Text)

Max Activating Token Index: 354

Text #10

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8805. Min Act: -0.1700

Data Index: 5771157 (Open Web Text)

Max Activating Token Index: 965

Text #11

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8804. Min Act: -0.1700

Data Index: 6835989 (Open Web Text)

Max Activating Token Index: 46

Text #12

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8841. Min Act: -0.1700

Data Index: 5452886 (Open Web Text)

Max Activating Token Index: 811

Text #13

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8789. Min Act: -0.1700

Data Index: 3391238 (Open Web Text)

Max Activating Token Index: 1010

Text #14

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8577. Min Act: -0.1700

Data Index: 40975 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8670. Min Act: -0.1700

Data Index: 5216744 (Open Web Text)

Max Activating Token Index: 909

Text #16

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8643. Min Act: -0.1700

Data Index: 8232497 (Open Web Text)

Max Activating Token Index: 147

Text #17

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8686. Min Act: -0.1700

Data Index: 3586249 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8652. Min Act: -0.1700

Data Index: 985878 (Open Web Text)

Max Activating Token Index: 101

Text #19

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.8550. Min Act: -0.1700

Data Index: 7952024 (Open Web Text)

Max Activating Token Index: 952