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

Dataset: Open Web Text

Neuron 1351 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: 0.8445. Min Range: -0.8445

Max Act: 0.8445. Min Act: -0.1700

Data Index: 3763577 (Open Web Text)

Max Activating Token Index: 186

Text #1

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8295. Min Act: -0.1700

Data Index: 5649875 (Open Web Text)

Max Activating Token Index: 187

Text #2

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8312. Min Act: -0.1700

Data Index: 2640278 (Open Web Text)

Max Activating Token Index: 203

Text #3

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8007. Min Act: -0.1700

Data Index: 6750638 (Open Web Text)

Max Activating Token Index: 191

Text #4

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8038. Min Act: -0.1700

Data Index: 2487415 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8064. Min Act: -0.1700

Data Index: 5043027 (Open Web Text)

Max Activating Token Index: 179

Text #6

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8077. Min Act: -0.1700

Data Index: 5000851 (Open Web Text)

Max Activating Token Index: 184

Text #7

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8037. Min Act: -0.1700

Data Index: 1677715 (Open Web Text)

Max Activating Token Index: 203

Text #8

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8103. Min Act: -0.1700

Data Index: 5889892 (Open Web Text)

Max Activating Token Index: 201

Text #9

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7991. Min Act: -0.1700

Data Index: 6812237 (Open Web Text)

Max Activating Token Index: 190

Text #10

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7971. Min Act: -0.1700

Data Index: 2637267 (Open Web Text)

Max Activating Token Index: 184

Text #11

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7963. Min Act: -0.1700

Data Index: 817146 (Open Web Text)

Max Activating Token Index: 182

Text #12

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7964. Min Act: -0.1700

Data Index: 6854011 (Open Web Text)

Max Activating Token Index: 194

Text #13

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7873. Min Act: -0.1700

Data Index: 1779897 (Open Web Text)

Max Activating Token Index: 172

Text #14

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7919. Min Act: -0.1700

Data Index: 5734311 (Open Web Text)

Max Activating Token Index: 163

Text #15

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7899. Min Act: -0.1700

Data Index: 3513088 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7923. Min Act: -0.1700

Data Index: 7692250 (Open Web Text)

Max Activating Token Index: 167

Text #17

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7956. Min Act: -0.1700

Data Index: 8553276 (Open Web Text)

Max Activating Token Index: 202

Text #18

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7936. Min Act: -0.1700

Data Index: 1295177 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.7915. Min Act: -0.1700

Data Index: 236531 (Open Web Text)

Max Activating Token Index: 164