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

Dataset: Open Web Text

Neuron 1546 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: 3.1173. Min Range: -3.1173

Max Act: 3.1173. Min Act: -0.1700

Data Index: 3416378 (Open Web Text)

Max Activating Token Index: 466

Text #1

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.1084. Min Act: -0.1700

Data Index: 5961706 (Open Web Text)

Max Activating Token Index: 970

Text #2

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0617. Min Act: -0.1700

Data Index: 8038614 (Open Web Text)

Max Activating Token Index: 399

Text #3

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0389. Min Act: -0.1700

Data Index: 5899758 (Open Web Text)

Max Activating Token Index: 1014

Text #4

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0271. Min Act: -0.1700

Data Index: 6570277 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0310. Min Act: -0.1700

Data Index: 750893 (Open Web Text)

Max Activating Token Index: 878

Text #6

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0358. Min Act: -0.1700

Data Index: 7319967 (Open Web Text)

Max Activating Token Index: 990

Text #7

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0240. Min Act: -0.1700

Data Index: 4276646 (Open Web Text)

Max Activating Token Index: 266

Text #8

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0195. Min Act: -0.1700

Data Index: 8117262 (Open Web Text)

Max Activating Token Index: 58

Text #9

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0157. Min Act: -0.1700

Data Index: 5288971 (Open Web Text)

Max Activating Token Index: 845

Text #10

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0256. Min Act: -0.1700

Data Index: 4907704 (Open Web Text)

Max Activating Token Index: 984

Text #11

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0130. Min Act: -0.1700

Data Index: 3640964 (Open Web Text)

Max Activating Token Index: 976

Text #12

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9759. Min Act: -0.1700

Data Index: 1079767 (Open Web Text)

Max Activating Token Index: 892

Text #13

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9829. Min Act: -0.1700

Data Index: 2595398 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9978. Min Act: -0.1700

Data Index: 4062819 (Open Web Text)

Max Activating Token Index: 179

Text #15

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9919. Min Act: -0.1700

Data Index: 224914 (Open Web Text)

Max Activating Token Index: 773

Text #16

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9987. Min Act: -0.1700

Data Index: 2443420 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0067. Min Act: -0.1700

Data Index: 193403 (Open Web Text)

Max Activating Token Index: 825

Text #18

Max Range: 3.1173. Min Range: -3.1173

Max Act: 3.0071. Min Act: -0.1700

Data Index: 3411244 (Open Web Text)

Max Activating Token Index: 663

Text #19

Max Range: 3.1173. Min Range: -3.1173

Max Act: 2.9791. Min Act: -0.1700

Data Index: 3705170 (Open Web Text)

Max Activating Token Index: 1019