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

Dataset: Open Web Text

Neuron 141 in Layer 5

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: 3.0074. Min Range: -3.0074

Max Act: 3.0074. Min Act: -0.1700

Data Index: 5484095 (Open Web Text)

Max Activating Token Index: 970

Text #1

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.9660. Min Act: -0.1700

Data Index: 6702063 (Open Web Text)

Max Activating Token Index: 534

Text #2

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.9261. Min Act: -0.1700

Data Index: 8381826 (Open Web Text)

Max Activating Token Index: 520

Text #3

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.9419. Min Act: -0.1700

Data Index: 6681682 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.9109. Min Act: -0.1700

Data Index: 1950812 (Open Web Text)

Max Activating Token Index: 225

Text #5

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.9132. Min Act: -0.1700

Data Index: 3432577 (Open Web Text)

Max Activating Token Index: 83

Text #6

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.8659. Min Act: -0.1700

Data Index: 4321921 (Open Web Text)

Max Activating Token Index: 130

Text #7

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.8548. Min Act: -0.1700

Data Index: 8599482 (Open Web Text)

Max Activating Token Index: 944

Text #8

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.8282. Min Act: -0.1700

Data Index: 8427080 (Open Web Text)

Max Activating Token Index: 152

Text #9

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.8329. Min Act: -0.1700

Data Index: 8526406 (Open Web Text)

Max Activating Token Index: 832

Text #10

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.8098. Min Act: -0.1700

Data Index: 3784112 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.8272. Min Act: -0.1700

Data Index: 7805638 (Open Web Text)

Max Activating Token Index: 306

Text #12

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.7934. Min Act: -0.1700

Data Index: 3533543 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.7940. Min Act: -0.1700

Data Index: 449362 (Open Web Text)

Max Activating Token Index: 980

Text #14

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.8023. Min Act: -0.1700

Data Index: 1911319 (Open Web Text)

Max Activating Token Index: 883

Text #15

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.7712. Min Act: -0.1700

Data Index: 5386590 (Open Web Text)

Max Activating Token Index: 959

Text #16

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.7458. Min Act: -0.1700

Data Index: 6754983 (Open Web Text)

Max Activating Token Index: 874

Text #17

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.7721. Min Act: -0.1700

Data Index: 4985709 (Open Web Text)

Max Activating Token Index: 245

Text #18

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.7719. Min Act: -0.1700

Data Index: 4025504 (Open Web Text)

Max Activating Token Index: 802

Text #19

Max Range: 3.0074. Min Range: -3.0074

Max Act: 2.7495. Min Act: -0.1700

Data Index: 1063974 (Open Web Text)

Max Activating Token Index: 846