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

Dataset: Open Web Text

Neuron 2956 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: 4.1835. Min Range: -4.1835

Max Act: 4.1814. Min Act: -0.1700

Data Index: 5889118 (Open Web Text)

Max Activating Token Index: 268

Text #1

Max Range: 4.1835. Min Range: -4.1835

Max Act: 4.1219. Min Act: -0.1700

Data Index: 6716310 (Open Web Text)

Max Activating Token Index: 896

Text #2

Max Range: 4.1835. Min Range: -4.1835

Max Act: 4.1835. Min Act: -0.1700

Data Index: 1435272 (Open Web Text)

Max Activating Token Index: 594

Text #3

Max Range: 4.1835. Min Range: -4.1835

Max Act: 4.1103. Min Act: -0.1700

Data Index: 4193051 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9575. Min Act: -0.1700

Data Index: 5417031 (Open Web Text)

Max Activating Token Index: 735

Text #5

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9949. Min Act: -0.1700

Data Index: 5905525 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9404. Min Act: -0.1700

Data Index: 2339186 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9187. Min Act: -0.1700

Data Index: 8305488 (Open Web Text)

Max Activating Token Index: 456

Text #8

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9036. Min Act: -0.1700

Data Index: 1706683 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9531. Min Act: -0.1700

Data Index: 8437149 (Open Web Text)

Max Activating Token Index: 827

Text #10

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.8805. Min Act: -0.1700

Data Index: 1664122 (Open Web Text)

Max Activating Token Index: 652

Text #11

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9166. Min Act: -0.1700

Data Index: 2154656 (Open Web Text)

Max Activating Token Index: 291

Text #12

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9249. Min Act: -0.1700

Data Index: 7680716 (Open Web Text)

Max Activating Token Index: 102

Text #13

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.8843. Min Act: -0.1700

Data Index: 7694647 (Open Web Text)

Max Activating Token Index: 1003

Text #14

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9066. Min Act: -0.1700

Data Index: 2151842 (Open Web Text)

Max Activating Token Index: 921

Text #15

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.9074. Min Act: -0.1700

Data Index: 6017627 (Open Web Text)

Max Activating Token Index: 858

Text #16

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.8549. Min Act: -0.1700

Data Index: 6301200 (Open Web Text)

Max Activating Token Index: 759

Text #17

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.8714. Min Act: -0.1700

Data Index: 1051719 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.8585. Min Act: -0.1700

Data Index: 602828 (Open Web Text)

Max Activating Token Index: 907

Text #19

Max Range: 4.1835. Min Range: -4.1835

Max Act: 3.8727. Min Act: -0.1700

Data Index: 6625795 (Open Web Text)

Max Activating Token Index: 924