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

Dataset: Open Web Text

Neuron 1384 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: 4.7108. Min Range: -4.7108

Max Act: 4.7108. Min Act: -0.1700

Data Index: 1245301 (Open Web Text)

Max Activating Token Index: 287

Text #1

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.6737. Min Act: -0.1700

Data Index: 8424677 (Open Web Text)

Max Activating Token Index: 395

Text #2

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.6484. Min Act: -0.1700

Data Index: 7558523 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.5958. Min Act: -0.1700

Data Index: 7761169 (Open Web Text)

Max Activating Token Index: 118

Text #4

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.5773. Min Act: -0.1700

Data Index: 6885594 (Open Web Text)

Max Activating Token Index: 611

Text #5

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.5227. Min Act: -0.1700

Data Index: 4667834 (Open Web Text)

Max Activating Token Index: 499

Text #6

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.5188. Min Act: -0.1700

Data Index: 590423 (Open Web Text)

Max Activating Token Index: 958

Text #7

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.5093. Min Act: -0.1700

Data Index: 3773312 (Open Web Text)

Max Activating Token Index: 372

Text #8

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.5069. Min Act: -0.1700

Data Index: 6527034 (Open Web Text)

Max Activating Token Index: 551

Text #9

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4868. Min Act: -0.1700

Data Index: 5930790 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4889. Min Act: -0.1700

Data Index: 2883268 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4961. Min Act: -0.1700

Data Index: 975822 (Open Web Text)

Max Activating Token Index: 146

Text #12

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4699. Min Act: -0.1700

Data Index: 1376956 (Open Web Text)

Max Activating Token Index: 222

Text #13

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4921. Min Act: -0.1700

Data Index: 4944825 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4689. Min Act: -0.1700

Data Index: 7815363 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.5031. Min Act: -0.1700

Data Index: 8204249 (Open Web Text)

Max Activating Token Index: 870

Text #16

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4703. Min Act: -0.1700

Data Index: 6897900 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4825. Min Act: -0.1700

Data Index: 1166516 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4769. Min Act: -0.1700

Data Index: 4511036 (Open Web Text)

Max Activating Token Index: 670

Text #19

Max Range: 4.7108. Min Range: -4.7108

Max Act: 4.4715. Min Act: -0.1700

Data Index: 1957048 (Open Web Text)

Max Activating Token Index: 293