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

Dataset: Open Web Text

Neuron 2485 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: 4.0108. Min Range: -4.0108

Max Act: 4.0108. Min Act: -0.1700

Data Index: 2943130 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.8952. Min Act: -0.1700

Data Index: 8545148 (Open Web Text)

Max Activating Token Index: 142

Text #2

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.8657. Min Act: -0.1700

Data Index: 4486853 (Open Web Text)

Max Activating Token Index: 225

Text #3

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.8566. Min Act: -0.1700

Data Index: 4569907 (Open Web Text)

Max Activating Token Index: 366

Text #4

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.8372. Min Act: -0.1700

Data Index: 8262504 (Open Web Text)

Max Activating Token Index: 435

Text #5

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7793. Min Act: -0.1700

Data Index: 3311829 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7908. Min Act: -0.1700

Data Index: 5471501 (Open Web Text)

Max Activating Token Index: 468

Text #7

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7787. Min Act: -0.1700

Data Index: 6478394 (Open Web Text)

Max Activating Token Index: 717

Text #8

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7721. Min Act: -0.1700

Data Index: 4417482 (Open Web Text)

Max Activating Token Index: 368

Text #9

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7879. Min Act: -0.1700

Data Index: 268269 (Open Web Text)

Max Activating Token Index: 362

Text #10

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7721. Min Act: -0.1700

Data Index: 4937895 (Open Web Text)

Max Activating Token Index: 667

Text #11

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7390. Min Act: -0.1700

Data Index: 6160869 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7307. Min Act: -0.1700

Data Index: 1516828 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7406. Min Act: -0.1700

Data Index: 3321366 (Open Web Text)

Max Activating Token Index: 663

Text #14

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7236. Min Act: -0.1700

Data Index: 3337567 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7150. Min Act: -0.1700

Data Index: 3092401 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7177. Min Act: -0.1700

Data Index: 3372453 (Open Web Text)

Max Activating Token Index: 912

Text #17

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.7037. Min Act: -0.1700

Data Index: 2480164 (Open Web Text)

Max Activating Token Index: 681

Text #18

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6963. Min Act: -0.1700

Data Index: 107356 (Open Web Text)

Max Activating Token Index: 429

Text #19

Max Range: 4.0108. Min Range: -4.0108

Max Act: 3.6918. Min Act: -0.1700

Data Index: 829276 (Open Web Text)

Max Activating Token Index: 276