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

Dataset: Open Web Text

Neuron 1393 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: 3.6569. Min Range: -3.6569

Max Act: 3.6569. Min Act: -0.1700

Data Index: 5465948 (Open Web Text)

Max Activating Token Index: 164

Text #1

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.6167. Min Act: -0.1700

Data Index: 4068013 (Open Web Text)

Max Activating Token Index: 870

Text #2

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.5647. Min Act: -0.1700

Data Index: 4396967 (Open Web Text)

Max Activating Token Index: 74

Text #3

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.5487. Min Act: -0.1700

Data Index: 7330630 (Open Web Text)

Max Activating Token Index: 709

Text #4

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.5055. Min Act: -0.1700

Data Index: 395932 (Open Web Text)

Max Activating Token Index: 752

Text #5

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.4814. Min Act: -0.1700

Data Index: 1917376 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.4497. Min Act: -0.1700

Data Index: 8569052 (Open Web Text)

Max Activating Token Index: 869

Text #7

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.4450. Min Act: -0.1700

Data Index: 2992627 (Open Web Text)

Max Activating Token Index: 273

Text #8

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.4472. Min Act: -0.1700

Data Index: 116961 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.4306. Min Act: -0.1700

Data Index: 2052230 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.4361. Min Act: -0.1700

Data Index: 1459252 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.4143. Min Act: -0.1700

Data Index: 1225086 (Open Web Text)

Max Activating Token Index: 479

Text #12

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3871. Min Act: -0.1700

Data Index: 4103808 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3869. Min Act: -0.1700

Data Index: 339378 (Open Web Text)

Max Activating Token Index: 263

Text #14

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3654. Min Act: -0.1700

Data Index: 5633641 (Open Web Text)

Max Activating Token Index: 364

Text #15

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3878. Min Act: -0.1700

Data Index: 5111457 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3698. Min Act: -0.1700

Data Index: 4275344 (Open Web Text)

Max Activating Token Index: 558

Text #17

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3549. Min Act: -0.1700

Data Index: 1442074 (Open Web Text)

Max Activating Token Index: 491

Text #18

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3219. Min Act: -0.1700

Data Index: 6784990 (Open Web Text)

Max Activating Token Index: 201

Text #19

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3584. Min Act: -0.1700

Data Index: 2085131 (Open Web Text)

Max Activating Token Index: 651