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

Dataset: Open Web Text

Neuron 807 in Layer 5

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: 4.1372. Min Range: -4.1372

Max Act: 4.1372. Min Act: -0.1700

Data Index: 3215275 (Open Web Text)

Max Activating Token Index: 448

Text #1

Max Range: 4.1372. Min Range: -4.1372

Max Act: 4.1210. Min Act: -0.1700

Data Index: 946763 (Open Web Text)

Max Activating Token Index: 345

Text #2

Max Range: 4.1372. Min Range: -4.1372

Max Act: 4.0607. Min Act: -0.1700

Data Index: 2582691 (Open Web Text)

Max Activating Token Index: 252

Text #3

Max Range: 4.1372. Min Range: -4.1372

Max Act: 4.0145. Min Act: -0.1700

Data Index: 6286637 (Open Web Text)

Max Activating Token Index: 922

Text #4

Max Range: 4.1372. Min Range: -4.1372

Max Act: 4.0333. Min Act: -0.1700

Data Index: 7278906 (Open Web Text)

Max Activating Token Index: 488

Text #5

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.9943. Min Act: -0.1700

Data Index: 7572162 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.9979. Min Act: -0.1700

Data Index: 3256876 (Open Web Text)

Max Activating Token Index: 537

Text #7

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.9863. Min Act: -0.1700

Data Index: 995737 (Open Web Text)

Max Activating Token Index: 561

Text #8

Max Range: 4.1372. Min Range: -4.1372

Max Act: 4.0090. Min Act: -0.1700

Data Index: 6001763 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.9595. Min Act: -0.1700

Data Index: 8794221 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.9072. Min Act: -0.1700

Data Index: 3064976 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.8849. Min Act: -0.1700

Data Index: 1183917 (Open Web Text)

Max Activating Token Index: 891

Text #12

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.8702. Min Act: -0.1700

Data Index: 595183 (Open Web Text)

Max Activating Token Index: 587

Text #13

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.9078. Min Act: -0.1700

Data Index: 3664093 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.8599. Min Act: -0.1700

Data Index: 8745992 (Open Web Text)

Max Activating Token Index: 408

Text #15

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.9208. Min Act: -0.1700

Data Index: 7140831 (Open Web Text)

Max Activating Token Index: 541

Text #16

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.8776. Min Act: -0.1700

Data Index: 7649174 (Open Web Text)

Max Activating Token Index: 412

Text #17

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.8740. Min Act: -0.1700

Data Index: 3664095 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.8662. Min Act: -0.1700

Data Index: 6383816 (Open Web Text)

Max Activating Token Index: 408

Text #19

Max Range: 4.1372. Min Range: -4.1372

Max Act: 3.8603. Min Act: -0.1700

Data Index: 5554574 (Open Web Text)

Max Activating Token Index: 376