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

Dataset: Open Web Text

Neuron 2240 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: 3.0377. Min Range: -3.0377

Max Act: 3.0377. Min Act: -0.1700

Data Index: 266288 (Open Web Text)

Max Activating Token Index: 293

Text #1

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8872. Min Act: -0.1700

Data Index: 266285 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8459. Min Act: -0.1700

Data Index: 2328980 (Open Web Text)

Max Activating Token Index: 180

Text #3

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8226. Min Act: -0.1700

Data Index: 2986765 (Open Web Text)

Max Activating Token Index: 833

Text #4

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8530. Min Act: -0.1700

Data Index: 3192258 (Open Web Text)

Max Activating Token Index: 576

Text #5

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8313. Min Act: -0.1700

Data Index: 586454 (Open Web Text)

Max Activating Token Index: 469

Text #6

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8468. Min Act: -0.1700

Data Index: 4947398 (Open Web Text)

Max Activating Token Index: 305

Text #7

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8248. Min Act: -0.1700

Data Index: 4475374 (Open Web Text)

Max Activating Token Index: 529

Text #8

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8195. Min Act: -0.1700

Data Index: 266290 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8320. Min Act: -0.1700

Data Index: 7956237 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8307. Min Act: -0.1700

Data Index: 6946674 (Open Web Text)

Max Activating Token Index: 366

Text #11

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.8029. Min Act: -0.1700

Data Index: 7196517 (Open Web Text)

Max Activating Token Index: 746

Text #12

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7950. Min Act: -0.1700

Data Index: 4318046 (Open Web Text)

Max Activating Token Index: 802

Text #13

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7786. Min Act: -0.1700

Data Index: 2896346 (Open Web Text)

Max Activating Token Index: 168

Text #14

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7947. Min Act: -0.1700

Data Index: 1706711 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7719. Min Act: -0.1700

Data Index: 6282844 (Open Web Text)

Max Activating Token Index: 797

Text #16

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7945. Min Act: -0.1700

Data Index: 4863136 (Open Web Text)

Max Activating Token Index: 220

Text #17

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7756. Min Act: -0.1700

Data Index: 7196512 (Open Web Text)

Max Activating Token Index: 105

Text #18

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7812. Min Act: -0.1700

Data Index: 7134026 (Open Web Text)

Max Activating Token Index: 893

Text #19

Max Range: 3.0377. Min Range: -3.0377

Max Act: 2.7963. Min Act: -0.1700

Data Index: 7538586 (Open Web Text)

Max Activating Token Index: 334