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

Dataset: Open Web Text

Neuron 1469 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: 4.1132. Min Range: -4.1132

Max Act: 4.1132. Min Act: -0.1700

Data Index: 1252051 (Open Web Text)

Max Activating Token Index: 943

Text #1

Max Range: 4.1132. Min Range: -4.1132

Max Act: 4.0418. Min Act: -0.1700

Data Index: 2891034 (Open Web Text)

Max Activating Token Index: 72

Text #2

Max Range: 4.1132. Min Range: -4.1132

Max Act: 4.0161. Min Act: -0.1700

Data Index: 6772084 (Open Web Text)

Max Activating Token Index: 587

Text #3

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.9499. Min Act: -0.1700

Data Index: 355014 (Open Web Text)

Max Activating Token Index: 399

Text #4

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.9172. Min Act: -0.1700

Data Index: 7561071 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.9478. Min Act: -0.1700

Data Index: 3791689 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.9721. Min Act: -0.1700

Data Index: 561081 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.9459. Min Act: -0.1700

Data Index: 1635510 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.9151. Min Act: -0.1700

Data Index: 4528543 (Open Web Text)

Max Activating Token Index: 486

Text #9

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.9060. Min Act: -0.1700

Data Index: 5252246 (Open Web Text)

Max Activating Token Index: 748

Text #10

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8928. Min Act: -0.1700

Data Index: 2968652 (Open Web Text)

Max Activating Token Index: 505

Text #11

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8892. Min Act: -0.1700

Data Index: 7465187 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8922. Min Act: -0.1700

Data Index: 5206712 (Open Web Text)

Max Activating Token Index: 912

Text #13

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8751. Min Act: -0.1700

Data Index: 2891033 (Open Web Text)

Max Activating Token Index: 869

Text #14

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8715. Min Act: -0.1700

Data Index: 4177788 (Open Web Text)

Max Activating Token Index: 317

Text #15

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8621. Min Act: -0.1700

Data Index: 5252244 (Open Web Text)

Max Activating Token Index: 120

Text #16

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8736. Min Act: -0.1700

Data Index: 4373016 (Open Web Text)

Max Activating Token Index: 317

Text #17

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8789. Min Act: -0.1700

Data Index: 1818661 (Open Web Text)

Max Activating Token Index: 305

Text #18

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8636. Min Act: -0.1700

Data Index: 3094954 (Open Web Text)

Max Activating Token Index: 886

Text #19

Max Range: 4.1132. Min Range: -4.1132

Max Act: 3.8501. Min Act: -0.1700

Data Index: 3084505 (Open Web Text)

Max Activating Token Index: 767