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

Dataset: Open Web Text

Neuron 1388 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: 0.9729. Min Range: -0.9729

Max Act: 0.9729. Min Act: -0.1700

Data Index: 5844881 (Open Web Text)

Max Activating Token Index: 747

Text #1

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.9489. Min Act: -0.1700

Data Index: 2049728 (Open Web Text)

Max Activating Token Index: 761

Text #2

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8897. Min Act: -0.1700

Data Index: 2485065 (Open Web Text)

Max Activating Token Index: 785

Text #3

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7925. Min Act: -0.1700

Data Index: 2485066 (Open Web Text)

Max Activating Token Index: 785

Text #4

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7833. Min Act: -0.1700

Data Index: 6557643 (Open Web Text)

Max Activating Token Index: 144

Text #5

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7807. Min Act: -0.1700

Data Index: 7624597 (Open Web Text)

Max Activating Token Index: 156

Text #6

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7662. Min Act: -0.1700

Data Index: 1081142 (Open Web Text)

Max Activating Token Index: 148

Text #7

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7648. Min Act: -0.1700

Data Index: 2318499 (Open Web Text)

Max Activating Token Index: 131

Text #8

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7548. Min Act: -0.1700

Data Index: 652455 (Open Web Text)

Max Activating Token Index: 122

Text #9

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7481. Min Act: -0.1700

Data Index: 2339476 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7539. Min Act: -0.1700

Data Index: 5364590 (Open Web Text)

Max Activating Token Index: 141

Text #11

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7434. Min Act: -0.1700

Data Index: 6757713 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7454. Min Act: -0.1700

Data Index: 1094781 (Open Web Text)

Max Activating Token Index: 122

Text #13

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7383. Min Act: -0.1700

Data Index: 1081141 (Open Web Text)

Max Activating Token Index: 152

Text #14

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7185. Min Act: -0.1700

Data Index: 6187340 (Open Web Text)

Max Activating Token Index: 864

Text #15

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7249. Min Act: -0.1700

Data Index: 8691326 (Open Web Text)

Max Activating Token Index: 141

Text #16

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7246. Min Act: -0.1700

Data Index: 8407307 (Open Web Text)

Max Activating Token Index: 127

Text #17

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7180. Min Act: -0.1700

Data Index: 7749695 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7149. Min Act: -0.1700

Data Index: 5885916 (Open Web Text)

Max Activating Token Index: 150

Text #19

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7153. Min Act: -0.1700

Data Index: 5848537 (Open Web Text)

Max Activating Token Index: 126