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

Dataset: Open Web Text

Neuron 2857 in Layer 4

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: 2.8036. Min Range: -2.8036

Max Act: 2.8036. Min Act: -0.1700

Data Index: 5496583 (Open Web Text)

Max Activating Token Index: 451

Text #1

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7888. Min Act: -0.1700

Data Index: 5840759 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7509. Min Act: -0.1700

Data Index: 219681 (Open Web Text)

Max Activating Token Index: 121

Text #3

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7589. Min Act: -0.1700

Data Index: 7167433 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7269. Min Act: -0.1700

Data Index: 1239155 (Open Web Text)

Max Activating Token Index: 507

Text #5

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6854. Min Act: -0.1700

Data Index: 515964 (Open Web Text)

Max Activating Token Index: 376

Text #6

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7357. Min Act: -0.1700

Data Index: 6511282 (Open Web Text)

Max Activating Token Index: 427

Text #7

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7522. Min Act: -0.1700

Data Index: 1876276 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7248. Min Act: -0.1700

Data Index: 7916094 (Open Web Text)

Max Activating Token Index: 743

Text #9

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7344. Min Act: -0.1700

Data Index: 2283116 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6979. Min Act: -0.1700

Data Index: 3260562 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.7043. Min Act: -0.1700

Data Index: 2412659 (Open Web Text)

Max Activating Token Index: 832

Text #12

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6771. Min Act: -0.1700

Data Index: 746388 (Open Web Text)

Max Activating Token Index: 657

Text #13

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6543. Min Act: -0.1700

Data Index: 5870090 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6330. Min Act: -0.1700

Data Index: 6044569 (Open Web Text)

Max Activating Token Index: 1006

Text #15

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6819. Min Act: -0.1700

Data Index: 8152476 (Open Web Text)

Max Activating Token Index: 841

Text #16

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6642. Min Act: -0.1700

Data Index: 810111 (Open Web Text)

Max Activating Token Index: 82

Text #17

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6089. Min Act: -0.1700

Data Index: 4722779 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6547. Min Act: -0.1700

Data Index: 8152477 (Open Web Text)

Max Activating Token Index: 59

Text #19

Max Range: 2.8036. Min Range: -2.8036

Max Act: 2.6462. Min Act: -0.1700

Data Index: 5693812 (Open Web Text)

Max Activating Token Index: 587