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

Dataset: Open Web Text

Neuron 621 in Layer 3

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: 4.4095. Min Range: -4.4095

Max Act: 4.4095. Min Act: -0.1700

Data Index: 2768952 (Open Web Text)

Max Activating Token Index: 26

Text #1

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.3503. Min Act: -0.1700

Data Index: 8551238 (Open Web Text)

Max Activating Token Index: 288

Text #2

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.3948. Min Act: -0.1700

Data Index: 4215788 (Open Web Text)

Max Activating Token Index: 130

Text #3

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.4011. Min Act: -0.1700

Data Index: 4892512 (Open Web Text)

Max Activating Token Index: 711

Text #4

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.3494. Min Act: -0.1700

Data Index: 6332274 (Open Web Text)

Max Activating Token Index: 118

Text #5

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.3687. Min Act: -0.1700

Data Index: 5875151 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.3455. Min Act: -0.1700

Data Index: 5474241 (Open Web Text)

Max Activating Token Index: 884

Text #7

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.2775. Min Act: -0.1700

Data Index: 8551033 (Open Web Text)

Max Activating Token Index: 65

Text #8

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.3330. Min Act: -0.1700

Data Index: 5529151 (Open Web Text)

Max Activating Token Index: 969

Text #9

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.3349. Min Act: -0.1700

Data Index: 3122409 (Open Web Text)

Max Activating Token Index: 120

Text #10

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.2895. Min Act: -0.1700

Data Index: 4912126 (Open Web Text)

Max Activating Token Index: 935

Text #11

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.2964. Min Act: -0.1700

Data Index: 7880207 (Open Web Text)

Max Activating Token Index: 838

Text #12

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.3023. Min Act: -0.1700

Data Index: 5174263 (Open Web Text)

Max Activating Token Index: 37

Text #13

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.3080. Min Act: -0.1700

Data Index: 5774497 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.2933. Min Act: -0.1700

Data Index: 706205 (Open Web Text)

Max Activating Token Index: 795

Text #15

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.2972. Min Act: -0.1700

Data Index: 201848 (Open Web Text)

Max Activating Token Index: 963

Text #16

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.2766. Min Act: -0.1700

Data Index: 3715330 (Open Web Text)

Max Activating Token Index: 975

Text #17

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.2932. Min Act: -0.1700

Data Index: 3939010 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.2818. Min Act: -0.1700

Data Index: 2537896 (Open Web Text)

Max Activating Token Index: 864

Text #19

Max Range: 4.4095. Min Range: -4.4095

Max Act: 4.2691. Min Act: -0.1700

Data Index: 7331171 (Open Web Text)

Max Activating Token Index: 378