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

Dataset: Open Web Text

Neuron 2169 in Layer 4

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: 4.0897. Min Range: -4.0897

Max Act: 4.0897. Min Act: -0.1700

Data Index: 5673861 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 4.0897. Min Range: -4.0897

Max Act: 4.0514. Min Act: -0.1700

Data Index: 2104738 (Open Web Text)

Max Activating Token Index: 366

Text #2

Max Range: 4.0897. Min Range: -4.0897

Max Act: 4.0019. Min Act: -0.1700

Data Index: 526478 (Open Web Text)

Max Activating Token Index: 718

Text #3

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.9841. Min Act: -0.1700

Data Index: 6934210 (Open Web Text)

Max Activating Token Index: 513

Text #4

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.9879. Min Act: -0.1700

Data Index: 2902794 (Open Web Text)

Max Activating Token Index: 407

Text #5

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.9511. Min Act: -0.1700

Data Index: 6982454 (Open Web Text)

Max Activating Token Index: 503

Text #6

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.9393. Min Act: -0.1700

Data Index: 4991760 (Open Web Text)

Max Activating Token Index: 512

Text #7

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.9226. Min Act: -0.1700

Data Index: 2126632 (Open Web Text)

Max Activating Token Index: 546

Text #8

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.9075. Min Act: -0.1700

Data Index: 8784126 (Open Web Text)

Max Activating Token Index: 535

Text #9

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8550. Min Act: -0.1700

Data Index: 6261181 (Open Web Text)

Max Activating Token Index: 996

Text #10

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8866. Min Act: -0.1700

Data Index: 8802529 (Open Web Text)

Max Activating Token Index: 920

Text #11

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.9022. Min Act: -0.1700

Data Index: 6966410 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8516. Min Act: -0.1700

Data Index: 7370201 (Open Web Text)

Max Activating Token Index: 369

Text #13

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8143. Min Act: -0.1700

Data Index: 7370203 (Open Web Text)

Max Activating Token Index: 1002

Text #14

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8169. Min Act: -0.1700

Data Index: 7390904 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8418. Min Act: -0.1700

Data Index: 4341723 (Open Web Text)

Max Activating Token Index: 932

Text #16

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.7827. Min Act: -0.1700

Data Index: 6359952 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8414. Min Act: -0.1700

Data Index: 5671209 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.8065. Min Act: -0.1700

Data Index: 5296863 (Open Web Text)

Max Activating Token Index: 976

Text #19

Max Range: 4.0897. Min Range: -4.0897

Max Act: 3.7747. Min Act: -0.1700

Data Index: 3729719 (Open Web Text)

Max Activating Token Index: 981