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

Dataset: Open Web Text

Neuron 2808 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: 4.4064. Min Range: -4.4064

Max Act: 4.3886. Min Act: -0.1700

Data Index: 4104327 (Open Web Text)

Max Activating Token Index: 471

Text #1

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.4064. Min Act: -0.1700

Data Index: 5586607 (Open Web Text)

Max Activating Token Index: 746

Text #2

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3389. Min Act: -0.1700

Data Index: 7895370 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3901. Min Act: -0.1700

Data Index: 6977394 (Open Web Text)

Max Activating Token Index: 377

Text #4

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3512. Min Act: -0.1700

Data Index: 8543682 (Open Web Text)

Max Activating Token Index: 301

Text #5

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3105. Min Act: -0.1700

Data Index: 7709500 (Open Web Text)

Max Activating Token Index: 48

Text #6

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3106. Min Act: -0.1700

Data Index: 6754347 (Open Web Text)

Max Activating Token Index: 436

Text #7

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3142. Min Act: -0.1700

Data Index: 6754342 (Open Web Text)

Max Activating Token Index: 427

Text #8

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3116. Min Act: -0.1700

Data Index: 257158 (Open Web Text)

Max Activating Token Index: 913

Text #9

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2365. Min Act: -0.1700

Data Index: 5031490 (Open Web Text)

Max Activating Token Index: 653

Text #10

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2939. Min Act: -0.1700

Data Index: 5356014 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2926. Min Act: -0.1700

Data Index: 6018063 (Open Web Text)

Max Activating Token Index: 744

Text #12

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2806. Min Act: -0.1700

Data Index: 2564890 (Open Web Text)

Max Activating Token Index: 567

Text #13

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2979. Min Act: -0.1700

Data Index: 3754050 (Open Web Text)

Max Activating Token Index: 467

Text #14

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3042. Min Act: -0.1700

Data Index: 2940721 (Open Web Text)

Max Activating Token Index: 541

Text #15

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2835. Min Act: -0.1700

Data Index: 8335016 (Open Web Text)

Max Activating Token Index: 639

Text #16

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2670. Min Act: -0.1700

Data Index: 3991218 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.3232. Min Act: -0.1700

Data Index: 565359 (Open Web Text)

Max Activating Token Index: 628

Text #18

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2375. Min Act: -0.1700

Data Index: 3764192 (Open Web Text)

Max Activating Token Index: 720

Text #19

Max Range: 4.4064. Min Range: -4.4064

Max Act: 4.2577. Min Act: -0.1700

Data Index: 1323326 (Open Web Text)

Max Activating Token Index: 459