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

Dataset: Open Web Text

Neuron 1954 in Layer 2

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: 2.6439. Min Range: -2.6439

Max Act: 2.6439. Min Act: -0.1700

Data Index: 883751 (Open Web Text)

Max Activating Token Index: 948

Text #1

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.6267. Min Act: -0.1700

Data Index: 7260621 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5757. Min Act: -0.1700

Data Index: 2396581 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5549. Min Act: -0.1700

Data Index: 7995420 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5474. Min Act: -0.1700

Data Index: 4760632 (Open Web Text)

Max Activating Token Index: 847

Text #5

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5365. Min Act: -0.1700

Data Index: 6178568 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5338. Min Act: -0.1700

Data Index: 7817226 (Open Web Text)

Max Activating Token Index: 290

Text #7

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5221. Min Act: -0.1700

Data Index: 1803290 (Open Web Text)

Max Activating Token Index: 847

Text #8

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5184. Min Act: -0.1700

Data Index: 5428348 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5129. Min Act: -0.1700

Data Index: 3890178 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.4903. Min Act: -0.1700

Data Index: 5812437 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5126. Min Act: -0.1700

Data Index: 5740524 (Open Web Text)

Max Activating Token Index: 602

Text #12

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5174. Min Act: -0.1700

Data Index: 3646099 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5089. Min Act: -0.1700

Data Index: 5689872 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5118. Min Act: -0.1700

Data Index: 1274208 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5030. Min Act: -0.1700

Data Index: 4996645 (Open Web Text)

Max Activating Token Index: 934

Text #16

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.5048. Min Act: -0.1700

Data Index: 1961147 (Open Web Text)

Max Activating Token Index: 48

Text #17

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.4460. Min Act: -0.1700

Data Index: 8371856 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.4641. Min Act: -0.1700

Data Index: 3382048 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.6439. Min Range: -2.6439

Max Act: 2.4835. Min Act: -0.1700

Data Index: 8357050 (Open Web Text)

Max Activating Token Index: 1023