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

Dataset: Open Web Text

Neuron 2113 in Layer 4

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: 3.0735. Min Range: -3.0735

Max Act: 3.0735. Min Act: -0.1700

Data Index: 1958062 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.9886. Min Act: -0.1700

Data Index: 8314585 (Open Web Text)

Max Activating Token Index: 974

Text #2

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.9308. Min Act: -0.1700

Data Index: 7762534 (Open Web Text)

Max Activating Token Index: 303

Text #3

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.9230. Min Act: -0.1700

Data Index: 3607191 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.9038. Min Act: -0.1700

Data Index: 6549910 (Open Web Text)

Max Activating Token Index: 1003

Text #5

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8787. Min Act: -0.1700

Data Index: 8431011 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8928. Min Act: -0.1700

Data Index: 1769162 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8888. Min Act: -0.1700

Data Index: 2955523 (Open Web Text)

Max Activating Token Index: 480

Text #8

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8544. Min Act: -0.1700

Data Index: 2688961 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8588. Min Act: -0.1700

Data Index: 6335857 (Open Web Text)

Max Activating Token Index: 390

Text #10

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8416. Min Act: -0.1700

Data Index: 8005034 (Open Web Text)

Max Activating Token Index: 976

Text #11

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8595. Min Act: -0.1700

Data Index: 8219726 (Open Web Text)

Max Activating Token Index: 438

Text #12

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8431. Min Act: -0.1700

Data Index: 4130230 (Open Web Text)

Max Activating Token Index: 189

Text #13

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8322. Min Act: -0.1700

Data Index: 1250318 (Open Web Text)

Max Activating Token Index: 998

Text #14

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8399. Min Act: -0.1700

Data Index: 5534582 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8484. Min Act: -0.1700

Data Index: 7618755 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8454. Min Act: -0.1700

Data Index: 2053786 (Open Web Text)

Max Activating Token Index: 892

Text #17

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8555. Min Act: -0.1700

Data Index: 5177026 (Open Web Text)

Max Activating Token Index: 82

Text #18

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8385. Min Act: -0.1700

Data Index: 4853597 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 3.0735. Min Range: -3.0735

Max Act: 2.8285. Min Act: -0.1700

Data Index: 5572138 (Open Web Text)

Max Activating Token Index: 437