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

Dataset: Open Web Text

Neuron 2876 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: 4.2229. Min Range: -4.2229

Max Act: 4.2229. Min Act: -0.1700

Data Index: 8665469 (Open Web Text)

Max Activating Token Index: 630

Text #1

Max Range: 4.2229. Min Range: -4.2229

Max Act: 4.1449. Min Act: -0.1700

Data Index: 2056835 (Open Web Text)

Max Activating Token Index: 194

Text #2

Max Range: 4.2229. Min Range: -4.2229

Max Act: 4.1000. Min Act: -0.1700

Data Index: 3941641 (Open Web Text)

Max Activating Token Index: 42

Text #3

Max Range: 4.2229. Min Range: -4.2229

Max Act: 4.0332. Min Act: -0.1700

Data Index: 1476170 (Open Web Text)

Max Activating Token Index: 438

Text #4

Max Range: 4.2229. Min Range: -4.2229

Max Act: 4.0674. Min Act: -0.1700

Data Index: 3010429 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 4.2229. Min Range: -4.2229

Max Act: 4.0227. Min Act: -0.1700

Data Index: 4353432 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 4.2229. Min Range: -4.2229

Max Act: 4.0153. Min Act: -0.1700

Data Index: 1643804 (Open Web Text)

Max Activating Token Index: 193

Text #7

Max Range: 4.2229. Min Range: -4.2229

Max Act: 4.0062. Min Act: -0.1700

Data Index: 8665472 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.9039. Min Act: -0.1700

Data Index: 4171048 (Open Web Text)

Max Activating Token Index: 566

Text #9

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.8938. Min Act: -0.1700

Data Index: 1426886 (Open Web Text)

Max Activating Token Index: 242

Text #10

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.8492. Min Act: -0.1700

Data Index: 969059 (Open Web Text)

Max Activating Token Index: 492

Text #11

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.8514. Min Act: -0.1700

Data Index: 4848012 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.8509. Min Act: -0.1700

Data Index: 7847654 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.8704. Min Act: -0.1700

Data Index: 5132104 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.8266. Min Act: -0.1700

Data Index: 8760263 (Open Web Text)

Max Activating Token Index: 164

Text #15

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.8355. Min Act: -0.1700

Data Index: 5856072 (Open Web Text)

Max Activating Token Index: 125

Text #16

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.8275. Min Act: -0.1700

Data Index: 2765272 (Open Web Text)

Max Activating Token Index: 612

Text #17

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.7958. Min Act: -0.1700

Data Index: 2279880 (Open Web Text)

Max Activating Token Index: 315

Text #18

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.7999. Min Act: -0.1700

Data Index: 7752377 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 4.2229. Min Range: -4.2229

Max Act: 3.7514. Min Act: -0.1700

Data Index: 4277852 (Open Web Text)

Max Activating Token Index: 281