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

Dataset: Open Web Text

Neuron 2649 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: 2.5202. Min Range: -2.5202

Max Act: 2.5029. Min Act: -0.1700

Data Index: 1130225 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4844. Min Act: -0.1700

Data Index: 8077011 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4817. Min Act: -0.1700

Data Index: 481720 (Open Web Text)

Max Activating Token Index: 701

Text #3

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.5202. Min Act: -0.1700

Data Index: 5016042 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4436. Min Act: -0.1700

Data Index: 5225708 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4234. Min Act: -0.1700

Data Index: 7434276 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4186. Min Act: -0.1700

Data Index: 6271212 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4064. Min Act: -0.1700

Data Index: 357638 (Open Web Text)

Max Activating Token Index: 766

Text #8

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4183. Min Act: -0.1700

Data Index: 2403441 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.3949. Min Act: -0.1700

Data Index: 8297008 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.3720. Min Act: -0.1700

Data Index: 450616 (Open Web Text)

Max Activating Token Index: 585

Text #11

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4280. Min Act: -0.1700

Data Index: 417224 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4065. Min Act: -0.1700

Data Index: 7869173 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4132. Min Act: -0.1700

Data Index: 8458822 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.4031. Min Act: -0.1700

Data Index: 6734078 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.3795. Min Act: -0.1700

Data Index: 6348248 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.3941. Min Act: -0.1700

Data Index: 3008841 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.3611. Min Act: -0.1700

Data Index: 4794347 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.3405. Min Act: -0.1700

Data Index: 6091119 (Open Web Text)

Max Activating Token Index: 251

Text #19

Max Range: 2.5202. Min Range: -2.5202

Max Act: 2.3704. Min Act: -0.1700

Data Index: 4134040 (Open Web Text)

Max Activating Token Index: 1023