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

Dataset: Open Web Text

Neuron 1121 in Layer 6

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: 2.9132. Min Range: -2.9132

Max Act: 2.9132. Min Act: -0.1700

Data Index: 4912238 (Open Web Text)

Max Activating Token Index: 836

Text #1

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8889. Min Act: -0.1700

Data Index: 8410007 (Open Web Text)

Max Activating Token Index: 629

Text #2

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8610. Min Act: -0.1700

Data Index: 8617080 (Open Web Text)

Max Activating Token Index: 114

Text #3

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8695. Min Act: -0.1700

Data Index: 4873138 (Open Web Text)

Max Activating Token Index: 818

Text #4

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8483. Min Act: -0.1700

Data Index: 3151368 (Open Web Text)

Max Activating Token Index: 716

Text #5

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8224. Min Act: -0.1700

Data Index: 3168992 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8408. Min Act: -0.1700

Data Index: 1788090 (Open Web Text)

Max Activating Token Index: 938

Text #7

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8449. Min Act: -0.1700

Data Index: 4625722 (Open Web Text)

Max Activating Token Index: 894

Text #8

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8258. Min Act: -0.1700

Data Index: 7996634 (Open Web Text)

Max Activating Token Index: 786

Text #9

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.7923. Min Act: -0.1700

Data Index: 2725937 (Open Web Text)

Max Activating Token Index: 578

Text #10

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8048. Min Act: -0.1700

Data Index: 8577771 (Open Web Text)

Max Activating Token Index: 409

Text #11

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8118. Min Act: -0.1700

Data Index: 1146424 (Open Web Text)

Max Activating Token Index: 454

Text #12

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8047. Min Act: -0.1700

Data Index: 1115309 (Open Web Text)

Max Activating Token Index: 570

Text #13

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.7958. Min Act: -0.1700

Data Index: 6425193 (Open Web Text)

Max Activating Token Index: 349

Text #14

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.8106. Min Act: -0.1700

Data Index: 7879510 (Open Web Text)

Max Activating Token Index: 670

Text #15

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.7822. Min Act: -0.1700

Data Index: 1989966 (Open Web Text)

Max Activating Token Index: 537

Text #16

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.7802. Min Act: -0.1700

Data Index: 649107 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.7984. Min Act: -0.1700

Data Index: 1314401 (Open Web Text)

Max Activating Token Index: 776

Text #18

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.7556. Min Act: -0.1700

Data Index: 5166952 (Open Web Text)

Max Activating Token Index: 74

Text #19

Max Range: 2.9132. Min Range: -2.9132

Max Act: 2.7465. Min Act: -0.1700

Data Index: 4593382 (Open Web Text)

Max Activating Token Index: 305