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

Dataset: Open Web Text

Neuron 2045 in Layer 6

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: 5.8465. Min Range: -5.8465

Max Act: 5.8465. Min Act: -0.1700

Data Index: 1281413 (Open Web Text)

Max Activating Token Index: 992

Text #1

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.7796. Min Act: -0.1700

Data Index: 2399024 (Open Web Text)

Max Activating Token Index: 196

Text #2

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.7989. Min Act: -0.1700

Data Index: 1159172 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.7940. Min Act: -0.1700

Data Index: 8807875 (Open Web Text)

Max Activating Token Index: 539

Text #4

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.7442. Min Act: -0.1700

Data Index: 4706184 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.6808. Min Act: -0.1700

Data Index: 6540163 (Open Web Text)

Max Activating Token Index: 801

Text #6

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.6274. Min Act: -0.1700

Data Index: 7881742 (Open Web Text)

Max Activating Token Index: 273

Text #7

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.6050. Min Act: -0.1700

Data Index: 6455633 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.5267. Min Act: -0.1700

Data Index: 2485504 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.5884. Min Act: -0.1700

Data Index: 3632375 (Open Web Text)

Max Activating Token Index: 596

Text #10

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.5667. Min Act: -0.1700

Data Index: 8546022 (Open Web Text)

Max Activating Token Index: 337

Text #11

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.5402. Min Act: -0.1700

Data Index: 5168325 (Open Web Text)

Max Activating Token Index: 462

Text #12

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.5488. Min Act: -0.1700

Data Index: 5396125 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.5268. Min Act: -0.1700

Data Index: 852637 (Open Web Text)

Max Activating Token Index: 488

Text #14

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.5135. Min Act: -0.1700

Data Index: 1524961 (Open Web Text)

Max Activating Token Index: 870

Text #15

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.5104. Min Act: -0.1700

Data Index: 568930 (Open Web Text)

Max Activating Token Index: 628

Text #16

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.5115. Min Act: -0.1700

Data Index: 5817164 (Open Web Text)

Max Activating Token Index: 739

Text #17

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.4801. Min Act: -0.1700

Data Index: 3537708 (Open Web Text)

Max Activating Token Index: 526

Text #18

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.4675. Min Act: -0.1700

Data Index: 431185 (Open Web Text)

Max Activating Token Index: 255

Text #19

Max Range: 5.8465. Min Range: -5.8465

Max Act: 5.4990. Min Act: -0.1700

Data Index: 2243050 (Open Web Text)

Max Activating Token Index: 802