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

Dataset: Open Web Text

Neuron 2341 in Layer 4

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: 3.6394. Min Range: -3.6394

Max Act: 3.6394. Min Act: -0.1700

Data Index: 6979468 (Open Web Text)

Max Activating Token Index: 1000

Text #1

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.6087. Min Act: -0.1700

Data Index: 3270567 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.4485. Min Act: -0.1700

Data Index: 5968121 (Open Web Text)

Max Activating Token Index: 71

Text #3

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.4149. Min Act: -0.1700

Data Index: 4391812 (Open Web Text)

Max Activating Token Index: 960

Text #4

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.3835. Min Act: -0.1700

Data Index: 7856194 (Open Web Text)

Max Activating Token Index: 923

Text #5

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.3283. Min Act: -0.1700

Data Index: 6963532 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.2520. Min Act: -0.1700

Data Index: 8775649 (Open Web Text)

Max Activating Token Index: 404

Text #7

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.2643. Min Act: -0.1700

Data Index: 4728374 (Open Web Text)

Max Activating Token Index: 404

Text #8

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.2082. Min Act: -0.1700

Data Index: 5615877 (Open Web Text)

Max Activating Token Index: 141

Text #9

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.2329. Min Act: -0.1700

Data Index: 5650390 (Open Web Text)

Max Activating Token Index: 542

Text #10

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.2090. Min Act: -0.1700

Data Index: 4692615 (Open Web Text)

Max Activating Token Index: 268

Text #11

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1956. Min Act: -0.1700

Data Index: 4762509 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.2098. Min Act: -0.1700

Data Index: 8725158 (Open Web Text)

Max Activating Token Index: 149

Text #13

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1753. Min Act: -0.1700

Data Index: 7707497 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1837. Min Act: -0.1700

Data Index: 5945098 (Open Web Text)

Max Activating Token Index: 73

Text #15

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1656. Min Act: -0.1700

Data Index: 4423872 (Open Web Text)

Max Activating Token Index: 531

Text #16

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1621. Min Act: -0.1700

Data Index: 792887 (Open Web Text)

Max Activating Token Index: 56

Text #17

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1687. Min Act: -0.1700

Data Index: 1589103 (Open Web Text)

Max Activating Token Index: 478

Text #18

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1517. Min Act: -0.1700

Data Index: 7182009 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 3.6394. Min Range: -3.6394

Max Act: 3.1309. Min Act: -0.1700

Data Index: 6274727 (Open Web Text)

Max Activating Token Index: 520