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

Dataset: Open Web Text

Neuron 996 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: 6.0795. Min Range: -6.0795

Max Act: 6.0724. Min Act: -0.1700

Data Index: 2113707 (Open Web Text)

Max Activating Token Index: 969

Text #1

Max Range: 6.0795. Min Range: -6.0795

Max Act: 6.0083. Min Act: -0.1700

Data Index: 8747089 (Open Web Text)

Max Activating Token Index: 319

Text #2

Max Range: 6.0795. Min Range: -6.0795

Max Act: 6.0068. Min Act: -0.1700

Data Index: 2745905 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 6.0795. Min Range: -6.0795

Max Act: 6.0049. Min Act: -0.1700

Data Index: 586410 (Open Web Text)

Max Activating Token Index: 797

Text #4

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9961. Min Act: -0.1700

Data Index: 7791913 (Open Web Text)

Max Activating Token Index: 938

Text #5

Max Range: 6.0795. Min Range: -6.0795

Max Act: 6.0310. Min Act: -0.1700

Data Index: 7453535 (Open Web Text)

Max Activating Token Index: 500

Text #6

Max Range: 6.0795. Min Range: -6.0795

Max Act: 6.0795. Min Act: -0.1700

Data Index: 665637 (Open Web Text)

Max Activating Token Index: 556

Text #7

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9496. Min Act: -0.1700

Data Index: 4806124 (Open Web Text)

Max Activating Token Index: 592

Text #8

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9826. Min Act: -0.1700

Data Index: 2533599 (Open Web Text)

Max Activating Token Index: 247

Text #9

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9542. Min Act: -0.1700

Data Index: 7660901 (Open Web Text)

Max Activating Token Index: 527

Text #10

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9910. Min Act: -0.1700

Data Index: 1665372 (Open Web Text)

Max Activating Token Index: 266

Text #11

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9367. Min Act: -0.1700

Data Index: 661838 (Open Web Text)

Max Activating Token Index: 285

Text #12

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.8617. Min Act: -0.1700

Data Index: 4403685 (Open Web Text)

Max Activating Token Index: 888

Text #13

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9398. Min Act: -0.1700

Data Index: 1016372 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9731. Min Act: -0.1700

Data Index: 1247145 (Open Web Text)

Max Activating Token Index: 823

Text #15

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9440. Min Act: -0.1700

Data Index: 5037807 (Open Web Text)

Max Activating Token Index: 559

Text #16

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9687. Min Act: -0.1700

Data Index: 2177442 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9136. Min Act: -0.1700

Data Index: 5120976 (Open Web Text)

Max Activating Token Index: 226

Text #18

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9770. Min Act: -0.1700

Data Index: 1548695 (Open Web Text)

Max Activating Token Index: 988

Text #19

Max Range: 6.0795. Min Range: -6.0795

Max Act: 5.9780. Min Act: -0.1700

Data Index: 4176316 (Open Web Text)

Max Activating Token Index: 865