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

Dataset: Open Web Text

Neuron 2637 in Layer 2

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: 4.0418. Min Range: -4.0418

Max Act: 4.0418. Min Act: -0.1700

Data Index: 5006937 (Open Web Text)

Max Activating Token Index: 225

Text #1

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9027. Min Act: -0.1700

Data Index: 2763936 (Open Web Text)

Max Activating Token Index: 386

Text #2

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9577. Min Act: -0.1700

Data Index: 6441601 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8978. Min Act: -0.1700

Data Index: 6110612 (Open Web Text)

Max Activating Token Index: 634

Text #4

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9138. Min Act: -0.1700

Data Index: 1428326 (Open Web Text)

Max Activating Token Index: 752

Text #5

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9191. Min Act: -0.1700

Data Index: 5981400 (Open Web Text)

Max Activating Token Index: 144

Text #6

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8910. Min Act: -0.1700

Data Index: 383132 (Open Web Text)

Max Activating Token Index: 842

Text #7

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9011. Min Act: -0.1700

Data Index: 2638948 (Open Web Text)

Max Activating Token Index: 277

Text #8

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9285. Min Act: -0.1700

Data Index: 7744931 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9063. Min Act: -0.1700

Data Index: 3145835 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9216. Min Act: -0.1700

Data Index: 6871229 (Open Web Text)

Max Activating Token Index: 294

Text #11

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8701. Min Act: -0.1700

Data Index: 8624035 (Open Web Text)

Max Activating Token Index: 991

Text #12

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9125. Min Act: -0.1700

Data Index: 4447271 (Open Web Text)

Max Activating Token Index: 983

Text #13

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8754. Min Act: -0.1700

Data Index: 7276818 (Open Web Text)

Max Activating Token Index: 141

Text #14

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8643. Min Act: -0.1700

Data Index: 5077758 (Open Web Text)

Max Activating Token Index: 136

Text #15

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8848. Min Act: -0.1700

Data Index: 7033443 (Open Web Text)

Max Activating Token Index: 492

Text #16

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.9058. Min Act: -0.1700

Data Index: 5105948 (Open Web Text)

Max Activating Token Index: 156

Text #17

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8895. Min Act: -0.1700

Data Index: 7897330 (Open Web Text)

Max Activating Token Index: 45

Text #18

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8435. Min Act: -0.1700

Data Index: 8023515 (Open Web Text)

Max Activating Token Index: 298

Text #19

Max Range: 4.0418. Min Range: -4.0418

Max Act: 3.8435. Min Act: -0.1700

Data Index: 454669 (Open Web Text)

Max Activating Token Index: 298