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

Dataset: Open Web Text

Neuron 124 in Layer 1

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: 1.7605. Min Range: -1.7605

Max Act: 1.7605. Min Act: -0.1700

Data Index: 6344177 (Open Web Text)

Max Activating Token Index: 165

Text #1

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7243. Min Act: -0.1700

Data Index: 1839441 (Open Web Text)

Max Activating Token Index: 683

Text #2

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7371. Min Act: -0.1700

Data Index: 6324592 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7195. Min Act: -0.1700

Data Index: 1323551 (Open Web Text)

Max Activating Token Index: 622

Text #4

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7093. Min Act: -0.1700

Data Index: 7026628 (Open Web Text)

Max Activating Token Index: 86

Text #5

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7101. Min Act: -0.1700

Data Index: 3642054 (Open Web Text)

Max Activating Token Index: 98

Text #6

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7151. Min Act: -0.1700

Data Index: 5939931 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7053. Min Act: -0.1700

Data Index: 4303989 (Open Web Text)

Max Activating Token Index: 49

Text #8

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.7073. Min Act: -0.1700

Data Index: 4048240 (Open Web Text)

Max Activating Token Index: 169

Text #9

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6926. Min Act: -0.1700

Data Index: 2441400 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6873. Min Act: -0.1700

Data Index: 4745412 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6897. Min Act: -0.1700

Data Index: 3458715 (Open Web Text)

Max Activating Token Index: 488

Text #12

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6913. Min Act: -0.1700

Data Index: 7712645 (Open Web Text)

Max Activating Token Index: 642

Text #13

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6873. Min Act: -0.1700

Data Index: 1338332 (Open Web Text)

Max Activating Token Index: 241

Text #14

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6821. Min Act: -0.1700

Data Index: 7717614 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6896. Min Act: -0.1700

Data Index: 2695969 (Open Web Text)

Max Activating Token Index: 194

Text #16

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6936. Min Act: -0.1700

Data Index: 1598762 (Open Web Text)

Max Activating Token Index: 491

Text #17

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6940. Min Act: -0.1700

Data Index: 8114106 (Open Web Text)

Max Activating Token Index: 561

Text #18

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6798. Min Act: -0.1700

Data Index: 2335091 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 1.7605. Min Range: -1.7605

Max Act: 1.6772. Min Act: -0.1700

Data Index: 6925285 (Open Web Text)

Max Activating Token Index: 562