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

Dataset: Open Web Text

Neuron 3034 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: 1.8293. Min Range: -1.8293

Max Act: 1.8293. Min Act: -0.1700

Data Index: 6097257 (Open Web Text)

Max Activating Token Index: 774

Text #1

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7907. Min Act: -0.1700

Data Index: 5424498 (Open Web Text)

Max Activating Token Index: 633

Text #2

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7927. Min Act: -0.1700

Data Index: 7887864 (Open Web Text)

Max Activating Token Index: 381

Text #3

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7556. Min Act: -0.1700

Data Index: 2702962 (Open Web Text)

Max Activating Token Index: 851

Text #4

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7370. Min Act: -0.1700

Data Index: 7143227 (Open Web Text)

Max Activating Token Index: 609

Text #5

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7104. Min Act: -0.1700

Data Index: 7098021 (Open Web Text)

Max Activating Token Index: 379

Text #6

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7227. Min Act: -0.1697

Data Index: 6097261 (Open Web Text)

Max Activating Token Index: 601

Text #7

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7166. Min Act: -0.1700

Data Index: 6809598 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7102. Min Act: -0.1700

Data Index: 6809599 (Open Web Text)

Max Activating Token Index: 46

Text #9

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7086. Min Act: -0.1700

Data Index: 997172 (Open Web Text)

Max Activating Token Index: 523

Text #10

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7109. Min Act: -0.1700

Data Index: 1110314 (Open Web Text)

Max Activating Token Index: 315

Text #11

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.7081. Min Act: -0.1700

Data Index: 5318570 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.6877. Min Act: -0.1700

Data Index: 498676 (Open Web Text)

Max Activating Token Index: 897

Text #13

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.6939. Min Act: -0.1700

Data Index: 1783804 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.6974. Min Act: -0.1700

Data Index: 8072674 (Open Web Text)

Max Activating Token Index: 81

Text #15

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.6976. Min Act: -0.1700

Data Index: 6132192 (Open Web Text)

Max Activating Token Index: 755

Text #16

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.6953. Min Act: -0.1700

Data Index: 122828 (Open Web Text)

Max Activating Token Index: 490

Text #17

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.6911. Min Act: -0.1700

Data Index: 6516496 (Open Web Text)

Max Activating Token Index: 112

Text #18

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.6899. Min Act: -0.1697

Data Index: 1128785 (Open Web Text)

Max Activating Token Index: 40

Text #19

Max Range: 1.8293. Min Range: -1.8293

Max Act: 1.6957. Min Act: -0.1700

Data Index: 7725866 (Open Web Text)

Max Activating Token Index: 703