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

Dataset: Open Web Text

Neuron 1129 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: 3.7951. Min Range: -3.7951

Max Act: 3.7951. Min Act: -0.1700

Data Index: 311457 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.7051. Min Act: -0.1700

Data Index: 4141588 (Open Web Text)

Max Activating Token Index: 572

Text #2

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5638. Min Act: -0.1700

Data Index: 5044163 (Open Web Text)

Max Activating Token Index: 608

Text #3

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5239. Min Act: -0.1700

Data Index: 5315256 (Open Web Text)

Max Activating Token Index: 202

Text #4

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5503. Min Act: -0.1700

Data Index: 8241555 (Open Web Text)

Max Activating Token Index: 993

Text #5

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5302. Min Act: -0.1700

Data Index: 4247190 (Open Web Text)

Max Activating Token Index: 648

Text #6

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5324. Min Act: -0.1700

Data Index: 3785231 (Open Web Text)

Max Activating Token Index: 959

Text #7

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5379. Min Act: -0.1700

Data Index: 6088404 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5276. Min Act: -0.1700

Data Index: 6705761 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5234. Min Act: -0.1700

Data Index: 8790841 (Open Web Text)

Max Activating Token Index: 561

Text #10

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5279. Min Act: -0.1700

Data Index: 2202124 (Open Web Text)

Max Activating Token Index: 53

Text #11

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5109. Min Act: -0.1700

Data Index: 5821235 (Open Web Text)

Max Activating Token Index: 83

Text #12

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.4982. Min Act: -0.1700

Data Index: 5600522 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5032. Min Act: -0.1700

Data Index: 3785233 (Open Web Text)

Max Activating Token Index: 972

Text #14

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5077. Min Act: -0.1700

Data Index: 6848220 (Open Web Text)

Max Activating Token Index: 140

Text #15

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.4965. Min Act: -0.1700

Data Index: 4174400 (Open Web Text)

Max Activating Token Index: 223

Text #16

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5015. Min Act: -0.1700

Data Index: 8672069 (Open Web Text)

Max Activating Token Index: 693

Text #17

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.4930. Min Act: -0.1700

Data Index: 6944981 (Open Web Text)

Max Activating Token Index: 50

Text #18

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.4678. Min Act: -0.1700

Data Index: 4873943 (Open Web Text)

Max Activating Token Index: 769

Text #19

Max Range: 3.7951. Min Range: -3.7951

Max Act: 3.5032. Min Act: -0.1700

Data Index: 791254 (Open Web Text)

Max Activating Token Index: 794