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

Dataset: Open Web Text

Neuron 950 in Layer 1

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: 0.6781. Min Range: -0.6781

Max Act: 0.6781. Min Act: -0.1700

Data Index: 2310876 (Open Web Text)

Max Activating Token Index: 172

Text #1

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6775. Min Act: -0.1700

Data Index: 7392704 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6672. Min Act: -0.1700

Data Index: 8152984 (Open Web Text)

Max Activating Token Index: 153

Text #3

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6654. Min Act: -0.1694

Data Index: 717065 (Open Web Text)

Max Activating Token Index: 138

Text #4

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6604. Min Act: -0.1700

Data Index: 5862947 (Open Web Text)

Max Activating Token Index: 156

Text #5

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6569. Min Act: -0.1700

Data Index: 2613126 (Open Web Text)

Max Activating Token Index: 184

Text #6

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6599. Min Act: -0.1699

Data Index: 5232785 (Open Web Text)

Max Activating Token Index: 171

Text #7

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6644. Min Act: -0.1700

Data Index: 374740 (Open Web Text)

Max Activating Token Index: 208

Text #8

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6490. Min Act: -0.1700

Data Index: 6839225 (Open Web Text)

Max Activating Token Index: 171

Text #9

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6469. Min Act: -0.1700

Data Index: 6185343 (Open Web Text)

Max Activating Token Index: 181

Text #10

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6431. Min Act: -0.1700

Data Index: 6852678 (Open Web Text)

Max Activating Token Index: 188

Text #11

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6498. Min Act: -0.1700

Data Index: 4938407 (Open Web Text)

Max Activating Token Index: 146

Text #12

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6448. Min Act: -0.1700

Data Index: 3670199 (Open Web Text)

Max Activating Token Index: 174

Text #13

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6305. Min Act: -0.1700

Data Index: 5090611 (Open Web Text)

Max Activating Token Index: 160

Text #14

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6335. Min Act: -0.1700

Data Index: 3592240 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6403. Min Act: -0.1700

Data Index: 5182241 (Open Web Text)

Max Activating Token Index: 195

Text #16

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6371. Min Act: -0.1699

Data Index: 167817 (Open Web Text)

Max Activating Token Index: 178

Text #17

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6416. Min Act: -0.1700

Data Index: 7605265 (Open Web Text)

Max Activating Token Index: 196

Text #18

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6333. Min Act: -0.1700

Data Index: 4667041 (Open Web Text)

Max Activating Token Index: 160

Text #19

Max Range: 0.6781. Min Range: -0.6781

Max Act: 0.6297. Min Act: -0.1700

Data Index: 1679777 (Open Web Text)

Max Activating Token Index: 195