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

Dataset: Open Web Text

Neuron 2419 in Layer 2

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: 3.2258. Min Range: -3.2258

Max Act: 3.2258. Min Act: -0.1700

Data Index: 2504163 (Open Web Text)

Max Activating Token Index: 915

Text #1

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.2064. Min Act: -0.1700

Data Index: 3065861 (Open Web Text)

Max Activating Token Index: 789

Text #2

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1968. Min Act: -0.1700

Data Index: 2504158 (Open Web Text)

Max Activating Token Index: 693

Text #3

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1650. Min Act: -0.1700

Data Index: 3065858 (Open Web Text)

Max Activating Token Index: 974

Text #4

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1872. Min Act: -0.1700

Data Index: 3065860 (Open Web Text)

Max Activating Token Index: 291

Text #5

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1630. Min Act: -0.1700

Data Index: 2504164 (Open Web Text)

Max Activating Token Index: 886

Text #6

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1673. Min Act: -0.1700

Data Index: 2504165 (Open Web Text)

Max Activating Token Index: 67

Text #7

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1499. Min Act: -0.1700

Data Index: 3065856 (Open Web Text)

Max Activating Token Index: 76

Text #8

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1656. Min Act: -0.1700

Data Index: 3604170 (Open Web Text)

Max Activating Token Index: 126

Text #9

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1529. Min Act: -0.1700

Data Index: 2504159 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1273. Min Act: -0.1700

Data Index: 2504166 (Open Web Text)

Max Activating Token Index: 280

Text #11

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1111. Min Act: -0.1700

Data Index: 5397566 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1111. Min Act: -0.1700

Data Index: 8108500 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1111. Min Act: -0.1700

Data Index: 2725253 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1023. Min Act: -0.1700

Data Index: 5862914 (Open Web Text)

Max Activating Token Index: 996

Text #15

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0869. Min Act: -0.1700

Data Index: 4337772 (Open Web Text)

Max Activating Token Index: 802

Text #16

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0426. Min Act: -0.1700

Data Index: 7826706 (Open Web Text)

Max Activating Token Index: 820

Text #17

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0743. Min Act: -0.1700

Data Index: 5626668 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0605. Min Act: -0.1700

Data Index: 8268397 (Open Web Text)

Max Activating Token Index: 954

Text #19

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0701. Min Act: -0.1700

Data Index: 2129230 (Open Web Text)

Max Activating Token Index: 900