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

Dataset: Open Web Text

Neuron 633 in Layer 0

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: 2.7865. Min Range: -2.7865

Max Act: 2.7865. Min Act: -0.1700

Data Index: 6169013 (Open Web Text)

Max Activating Token Index: 145

Text #1

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7232. Min Act: -0.1700

Data Index: 3471420 (Open Web Text)

Max Activating Token Index: 147

Text #2

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7148. Min Act: -0.1700

Data Index: 7565273 (Open Web Text)

Max Activating Token Index: 135

Text #3

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7082. Min Act: -0.1700

Data Index: 7271394 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6945. Min Act: -0.1700

Data Index: 6923516 (Open Web Text)

Max Activating Token Index: 138

Text #5

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7047. Min Act: -0.1700

Data Index: 4382279 (Open Web Text)

Max Activating Token Index: 140

Text #6

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7021. Min Act: -0.1700

Data Index: 1731159 (Open Web Text)

Max Activating Token Index: 137

Text #7

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6913. Min Act: -0.1700

Data Index: 2534326 (Open Web Text)

Max Activating Token Index: 144

Text #8

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7020. Min Act: -0.1700

Data Index: 348358 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.7115. Min Act: -0.1700

Data Index: 6103476 (Open Web Text)

Max Activating Token Index: 142

Text #10

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6885. Min Act: -0.1700

Data Index: 6563263 (Open Web Text)

Max Activating Token Index: 150

Text #11

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6707. Min Act: -0.1700

Data Index: 5964247 (Open Web Text)

Max Activating Token Index: 137

Text #12

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6628. Min Act: -0.1700

Data Index: 3453339 (Open Web Text)

Max Activating Token Index: 151

Text #13

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6699. Min Act: -0.1700

Data Index: 2837785 (Open Web Text)

Max Activating Token Index: 143

Text #14

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6720. Min Act: -0.1700

Data Index: 5925410 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6699. Min Act: -0.1700

Data Index: 5803307 (Open Web Text)

Max Activating Token Index: 155

Text #16

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6678. Min Act: -0.1700

Data Index: 1552663 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6580. Min Act: -0.1700

Data Index: 4884120 (Open Web Text)

Max Activating Token Index: 133

Text #18

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6732. Min Act: -0.1700

Data Index: 388840 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 2.7865. Min Range: -2.7865

Max Act: 2.6692. Min Act: -0.1700

Data Index: 4813954 (Open Web Text)

Max Activating Token Index: 148