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

Dataset: Open Web Text

Neuron 2454 in Layer 0

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: 0.8501. Min Range: -0.8501

Max Act: 0.8448. Min Act: 0.0106

Data Index: 8558032 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8501. Min Act: -0.0013

Data Index: 931102 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8305. Min Act: -0.0193

Data Index: 4677933 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8153. Min Act: -0.0094

Data Index: 2049967 (Open Web Text)

Max Activating Token Index: 200

Text #4

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8230. Min Act: -0.0025

Data Index: 280175 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8260. Min Act: -0.0336

Data Index: 715193 (Open Web Text)

Max Activating Token Index: 1018

Text #6

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8179. Min Act: -0.0270

Data Index: 704625 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8125. Min Act: -0.0282

Data Index: 5316599 (Open Web Text)

Max Activating Token Index: 186

Text #8

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8124. Min Act: -0.0185

Data Index: 8423549 (Open Web Text)

Max Activating Token Index: 217

Text #9

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8123. Min Act: -0.0034

Data Index: 2613622 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8028. Min Act: -0.0348

Data Index: 609677 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8104. Min Act: -0.0199

Data Index: 1719554 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8100. Min Act: 0.0216

Data Index: 3638900 (Open Web Text)

Max Activating Token Index: 209

Text #13

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8040. Min Act: -0.0115

Data Index: 939136 (Open Web Text)

Max Activating Token Index: 211

Text #14

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8043. Min Act: 0.0060

Data Index: 4749866 (Open Web Text)

Max Activating Token Index: 204

Text #15

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8092. Min Act: -0.0088

Data Index: 1772760 (Open Web Text)

Max Activating Token Index: 181

Text #16

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8028. Min Act: -0.0363

Data Index: 5054105 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8076. Min Act: 0.0115

Data Index: 363044 (Open Web Text)

Max Activating Token Index: 185

Text #18

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8061. Min Act: -0.0270

Data Index: 832563 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8074. Min Act: -0.0487

Data Index: 4665761 (Open Web Text)

Max Activating Token Index: 220