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

Dataset: Open Web Text

Neuron 1212 in Layer 6

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: 3.5374. Min Range: -3.5374

Max Act: 3.5374. Min Act: -0.1700

Data Index: 1545052 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.4916. Min Act: -0.1700

Data Index: 5488823 (Open Web Text)

Max Activating Token Index: 849

Text #2

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.4494. Min Act: -0.1700

Data Index: 6130782 (Open Web Text)

Max Activating Token Index: 1019

Text #3

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.3759. Min Act: -0.1700

Data Index: 8301090 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.3260. Min Act: -0.1700

Data Index: 1355317 (Open Web Text)

Max Activating Token Index: 452

Text #5

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.3158. Min Act: -0.1700

Data Index: 6106786 (Open Web Text)

Max Activating Token Index: 678

Text #6

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2990. Min Act: -0.1700

Data Index: 3242363 (Open Web Text)

Max Activating Token Index: 315

Text #7

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.3139. Min Act: -0.1700

Data Index: 243268 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2994. Min Act: -0.1700

Data Index: 809676 (Open Web Text)

Max Activating Token Index: 484

Text #9

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2922. Min Act: -0.1700

Data Index: 5688311 (Open Web Text)

Max Activating Token Index: 961

Text #10

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2954. Min Act: -0.1700

Data Index: 7410884 (Open Web Text)

Max Activating Token Index: 679

Text #11

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2997. Min Act: -0.1700

Data Index: 7978047 (Open Web Text)

Max Activating Token Index: 986

Text #12

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.3103. Min Act: -0.1700

Data Index: 4767339 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2770. Min Act: -0.1700

Data Index: 6577653 (Open Web Text)

Max Activating Token Index: 35

Text #14

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.3000. Min Act: -0.1700

Data Index: 3429163 (Open Web Text)

Max Activating Token Index: 182

Text #15

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2627. Min Act: -0.1700

Data Index: 3343105 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2596. Min Act: -0.1700

Data Index: 4777772 (Open Web Text)

Max Activating Token Index: 947

Text #17

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2687. Min Act: -0.1700

Data Index: 5228052 (Open Web Text)

Max Activating Token Index: 160

Text #18

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2541. Min Act: -0.1700

Data Index: 3963264 (Open Web Text)

Max Activating Token Index: 105

Text #19

Max Range: 3.5374. Min Range: -3.5374

Max Act: 3.2699. Min Act: -0.1700

Data Index: 1639842 (Open Web Text)

Max Activating Token Index: 338