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

Dataset: Open Web Text

Neuron 787 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: 4.4861. Min Range: -4.4861

Max Act: 4.4861. Min Act: -0.1128

Data Index: 2941520 (Open Web Text)

Max Activating Token Index: 1

Text #1

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.4861. Min Act: -0.1128

Data Index: 5376641 (Open Web Text)

Max Activating Token Index: 1

Text #2

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.3646. Min Act: -0.1128

Data Index: 1104854 (Open Web Text)

Max Activating Token Index: 1

Text #3

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.3646. Min Act: -0.1128

Data Index: 6770246 (Open Web Text)

Max Activating Token Index: 1

Text #4

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.3646. Min Act: -0.1128

Data Index: 2592248 (Open Web Text)

Max Activating Token Index: 1

Text #5

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2877. Min Act: -0.1128

Data Index: 2744995 (Open Web Text)

Max Activating Token Index: 1

Text #6

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2877. Min Act: -0.1128

Data Index: 1373913 (Open Web Text)

Max Activating Token Index: 1

Text #7

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2877. Min Act: -0.1128

Data Index: 7856227 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2626. Min Act: -0.1128

Data Index: 3651487 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2754. Min Act: -0.1128

Data Index: 3926706 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2754. Min Act: -0.1128

Data Index: 4296137 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2754. Min Act: -0.1128

Data Index: 2544996 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2626. Min Act: -0.1128

Data Index: 5090869 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2626. Min Act: -0.1128

Data Index: 2830010 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2626. Min Act: -0.1128

Data Index: 868151 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2754. Min Act: -0.1128

Data Index: 1343970 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2626. Min Act: -0.1128

Data Index: 3486049 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2754. Min Act: -0.1128

Data Index: 965560 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2626. Min Act: -0.1128

Data Index: 5607024 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 4.4861. Min Range: -4.4861

Max Act: 4.2626. Min Act: -0.1128

Data Index: 3527039 (Open Web Text)

Max Activating Token Index: 1