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

Dataset: Open Web Text

Neuron 1496 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: 5.0174. Min Range: -5.0174

Max Act: 5.0174. Min Act: -0.1700

Data Index: 8420807 (Open Web Text)

Max Activating Token Index: 241

Text #1

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.9169. Min Act: -0.1700

Data Index: 529437 (Open Web Text)

Max Activating Token Index: 157

Text #2

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.9196. Min Act: -0.1700

Data Index: 165301 (Open Web Text)

Max Activating Token Index: 460

Text #3

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.9539. Min Act: -0.1700

Data Index: 6829629 (Open Web Text)

Max Activating Token Index: 551

Text #4

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.8847. Min Act: -0.1700

Data Index: 7912845 (Open Web Text)

Max Activating Token Index: 574

Text #5

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.7978. Min Act: -0.1700

Data Index: 3552322 (Open Web Text)

Max Activating Token Index: 435

Text #6

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.7405. Min Act: -0.1700

Data Index: 6392351 (Open Web Text)

Max Activating Token Index: 698

Text #7

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.8259. Min Act: -0.1700

Data Index: 5643316 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.8098. Min Act: -0.1700

Data Index: 8641649 (Open Web Text)

Max Activating Token Index: 976

Text #9

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.6685. Min Act: -0.1700

Data Index: 5148939 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.6971. Min Act: -0.1700

Data Index: 1113826 (Open Web Text)

Max Activating Token Index: 224

Text #11

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.6758. Min Act: -0.1700

Data Index: 6908019 (Open Web Text)

Max Activating Token Index: 564

Text #12

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.6062. Min Act: -0.1700

Data Index: 7463500 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.6356. Min Act: -0.1700

Data Index: 3772161 (Open Web Text)

Max Activating Token Index: 333

Text #14

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.6236. Min Act: -0.1700

Data Index: 15085 (Open Web Text)

Max Activating Token Index: 532

Text #15

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.6364. Min Act: -0.1700

Data Index: 817978 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.6298. Min Act: -0.1700

Data Index: 8680378 (Open Web Text)

Max Activating Token Index: 740

Text #17

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.6837. Min Act: -0.1700

Data Index: 1267762 (Open Web Text)

Max Activating Token Index: 984

Text #18

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.5308. Min Act: -0.1700

Data Index: 225955 (Open Web Text)

Max Activating Token Index: 871

Text #19

Max Range: 5.0174. Min Range: -5.0174

Max Act: 4.5597. Min Act: -0.1700

Data Index: 2673821 (Open Web Text)

Max Activating Token Index: 660