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

Dataset: Open Web Text

Neuron 2636 in Layer 2

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: 1.9027. Min Range: -1.9027

Max Act: 1.9027. Min Act: -0.1700

Data Index: 4475549 (Open Web Text)

Max Activating Token Index: 68

Text #1

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.8737. Min Act: -0.1700

Data Index: 2202707 (Open Web Text)

Max Activating Token Index: 245

Text #2

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.8600. Min Act: -0.1700

Data Index: 7170496 (Open Web Text)

Max Activating Token Index: 349

Text #3

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.8227. Min Act: -0.1700

Data Index: 3356941 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.8070. Min Act: -0.1700

Data Index: 1958158 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7979. Min Act: -0.1700

Data Index: 7597368 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.8135. Min Act: -0.1698

Data Index: 7810907 (Open Web Text)

Max Activating Token Index: 162

Text #7

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7977. Min Act: -0.1700

Data Index: 6155073 (Open Web Text)

Max Activating Token Index: 948

Text #8

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7955. Min Act: -0.1700

Data Index: 219339 (Open Web Text)

Max Activating Token Index: 445

Text #9

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7858. Min Act: -0.1700

Data Index: 6605242 (Open Web Text)

Max Activating Token Index: 232

Text #10

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7825. Min Act: -0.1700

Data Index: 5119013 (Open Web Text)

Max Activating Token Index: 97

Text #11

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7893. Min Act: -0.1700

Data Index: 1730856 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7724. Min Act: -0.1700

Data Index: 552751 (Open Web Text)

Max Activating Token Index: 229

Text #13

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7655. Min Act: -0.1700

Data Index: 4017201 (Open Web Text)

Max Activating Token Index: 72

Text #14

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7678. Min Act: -0.1700

Data Index: 7798693 (Open Web Text)

Max Activating Token Index: 201

Text #15

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7596. Min Act: -0.1700

Data Index: 3878883 (Open Web Text)

Max Activating Token Index: 738

Text #16

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7617. Min Act: -0.1700

Data Index: 4541008 (Open Web Text)

Max Activating Token Index: 441

Text #17

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7586. Min Act: -0.1700

Data Index: 2056033 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7659. Min Act: -0.1696

Data Index: 3995989 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 1.9027. Min Range: -1.9027

Max Act: 1.7662. Min Act: -0.1700

Data Index: 4427567 (Open Web Text)

Max Activating Token Index: 845