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

Dataset: Open Web Text

Neuron 1136 in Layer 1

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: 1.6093. Min Range: -1.6093

Max Act: 1.6093. Min Act: -0.1700

Data Index: 859043 (Open Web Text)

Max Activating Token Index: 576

Text #1

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5828. Min Act: -0.1700

Data Index: 7444126 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5796. Min Act: -0.1700

Data Index: 8288164 (Open Web Text)

Max Activating Token Index: 158

Text #3

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5781. Min Act: -0.1700

Data Index: 7345228 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5718. Min Act: -0.1700

Data Index: 3302306 (Open Web Text)

Max Activating Token Index: 920

Text #5

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5723. Min Act: -0.1700

Data Index: 2211259 (Open Web Text)

Max Activating Token Index: 295

Text #6

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5720. Min Act: -0.1700

Data Index: 6402747 (Open Web Text)

Max Activating Token Index: 718

Text #7

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5721. Min Act: -0.1700

Data Index: 1079290 (Open Web Text)

Max Activating Token Index: 905

Text #8

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5589. Min Act: -0.1700

Data Index: 1339173 (Open Web Text)

Max Activating Token Index: 213

Text #9

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5589. Min Act: -0.1700

Data Index: 2786561 (Open Web Text)

Max Activating Token Index: 72

Text #10

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5659. Min Act: -0.1700

Data Index: 7602100 (Open Web Text)

Max Activating Token Index: 125

Text #11

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5570. Min Act: -0.1700

Data Index: 5081178 (Open Web Text)

Max Activating Token Index: 763

Text #12

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5602. Min Act: -0.1700

Data Index: 4913847 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5515. Min Act: -0.1700

Data Index: 2892682 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5549. Min Act: -0.1700

Data Index: 6317116 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5516. Min Act: -0.1700

Data Index: 5555413 (Open Web Text)

Max Activating Token Index: 215

Text #16

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5547. Min Act: -0.1700

Data Index: 8105816 (Open Web Text)

Max Activating Token Index: 173

Text #17

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5532. Min Act: -0.1700

Data Index: 230039 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5418. Min Act: -0.1686

Data Index: 1422798 (Open Web Text)

Max Activating Token Index: 430

Text #19

Max Range: 1.6093. Min Range: -1.6093

Max Act: 1.5407. Min Act: -0.1700

Data Index: 7779801 (Open Web Text)

Max Activating Token Index: 242