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

Dataset: Open Web Text

Neuron 1969 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: 3.0717. Min Range: -3.0717

Max Act: 3.0717. Min Act: -0.1700

Data Index: 273246 (Open Web Text)

Max Activating Token Index: 253

Text #1

Max Range: 3.0717. Min Range: -3.0717

Max Act: 3.0400. Min Act: -0.1700

Data Index: 3409083 (Open Web Text)

Max Activating Token Index: 242

Text #2

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.9332. Min Act: -0.1700

Data Index: 4122598 (Open Web Text)

Max Activating Token Index: 371

Text #3

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8729. Min Act: -0.1700

Data Index: 5550049 (Open Web Text)

Max Activating Token Index: 889

Text #4

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8862. Min Act: -0.1700

Data Index: 7787717 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8682. Min Act: -0.1700

Data Index: 3920302 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8751. Min Act: -0.1700

Data Index: 970 (Open Web Text)

Max Activating Token Index: 383

Text #7

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8819. Min Act: -0.1700

Data Index: 1660420 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8823. Min Act: -0.1700

Data Index: 2930030 (Open Web Text)

Max Activating Token Index: 145

Text #9

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8731. Min Act: -0.1700

Data Index: 6857405 (Open Web Text)

Max Activating Token Index: 893

Text #10

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8498. Min Act: -0.1700

Data Index: 1723462 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8119. Min Act: -0.1700

Data Index: 6726943 (Open Web Text)

Max Activating Token Index: 754

Text #12

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8290. Min Act: -0.1700

Data Index: 8318526 (Open Web Text)

Max Activating Token Index: 136

Text #13

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8169. Min Act: -0.1700

Data Index: 4659144 (Open Web Text)

Max Activating Token Index: 668

Text #14

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8255. Min Act: -0.1700

Data Index: 5727655 (Open Web Text)

Max Activating Token Index: 164

Text #15

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8251. Min Act: -0.1700

Data Index: 7648562 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8350. Min Act: -0.1700

Data Index: 5671411 (Open Web Text)

Max Activating Token Index: 343

Text #17

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.7897. Min Act: -0.1700

Data Index: 26099 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8498. Min Act: -0.1700

Data Index: 1925686 (Open Web Text)

Max Activating Token Index: 235

Text #19

Max Range: 3.0717. Min Range: -3.0717

Max Act: 2.8200. Min Act: -0.1700

Data Index: 1342912 (Open Web Text)

Max Activating Token Index: 348