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

Dataset: Open Web Text

Neuron 287 in Layer 0

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: 3.2632. Min Range: -3.2632

Max Act: 3.2591. Min Act: -0.1700

Data Index: 1122095 (Open Web Text)

Max Activating Token Index: 855

Text #1

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2632. Min Act: -0.1700

Data Index: 5319971 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2561. Min Act: -0.1700

Data Index: 6971343 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2220. Min Act: -0.1700

Data Index: 7181267 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2277. Min Act: -0.1700

Data Index: 4088187 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2219. Min Act: -0.1700

Data Index: 4092953 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1934. Min Act: -0.1700

Data Index: 2490693 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2074. Min Act: -0.1700

Data Index: 8548920 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2074. Min Act: -0.1700

Data Index: 8543433 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2074. Min Act: -0.1700

Data Index: 6582582 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2074. Min Act: -0.1700

Data Index: 8388915 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2074. Min Act: -0.1700

Data Index: 691949 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2074. Min Act: -0.1700

Data Index: 54057 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2074. Min Act: -0.1700

Data Index: 5609709 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2017. Min Act: -0.1700

Data Index: 4201338 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1832. Min Act: -0.1700

Data Index: 117030 (Open Web Text)

Max Activating Token Index: 434

Text #16

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1913. Min Act: -0.1700

Data Index: 7130185 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1659. Min Act: -0.1700

Data Index: 7997791 (Open Web Text)

Max Activating Token Index: 373

Text #18

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1712. Min Act: -0.1700

Data Index: 5779301 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1717. Min Act: -0.1700

Data Index: 3251205 (Open Web Text)

Max Activating Token Index: 24