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

Dataset: Open Web Text

Neuron 610 in Layer 1

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: 2.4499. Min Range: -2.4499

Max Act: 2.4499. Min Act: -0.1700

Data Index: 2038753 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.4118. Min Act: -0.1700

Data Index: 5853090 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3887. Min Act: -0.1700

Data Index: 4290178 (Open Web Text)

Max Activating Token Index: 1021

Text #3

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3949. Min Act: -0.1700

Data Index: 5339117 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3968. Min Act: -0.1700

Data Index: 2423670 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3804. Min Act: -0.1700

Data Index: 2510546 (Open Web Text)

Max Activating Token Index: 1020

Text #6

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3830. Min Act: -0.1700

Data Index: 1453533 (Open Web Text)

Max Activating Token Index: 1017

Text #7

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3789. Min Act: -0.1700

Data Index: 326352 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3770. Min Act: -0.1700

Data Index: 4793792 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3820. Min Act: -0.1700

Data Index: 1355001 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3741. Min Act: -0.1700

Data Index: 2435831 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3574. Min Act: -0.1700

Data Index: 6411579 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3600. Min Act: -0.1700

Data Index: 4706980 (Open Web Text)

Max Activating Token Index: 1016

Text #13

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3632. Min Act: -0.1700

Data Index: 5628325 (Open Web Text)

Max Activating Token Index: 1022

Text #14

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3761. Min Act: -0.1700

Data Index: 7249970 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3694. Min Act: -0.1700

Data Index: 4594775 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3720. Min Act: -0.1700

Data Index: 6978527 (Open Web Text)

Max Activating Token Index: 1021

Text #17

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3692. Min Act: -0.1700

Data Index: 1609977 (Open Web Text)

Max Activating Token Index: 1017

Text #18

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3565. Min Act: -0.1700

Data Index: 6211054 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 2.4499. Min Range: -2.4499

Max Act: 2.3424. Min Act: -0.1700

Data Index: 3993531 (Open Web Text)

Max Activating Token Index: 1015