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

Dataset: Open Web Text

Neuron 101 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: 3.3110. Min Range: -3.3110

Max Act: 3.3110. Min Act: -0.1700

Data Index: 8585604 (Open Web Text)

Max Activating Token Index: 720

Text #1

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.2935. Min Act: -0.1700

Data Index: 1701774 (Open Web Text)

Max Activating Token Index: 944

Text #2

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.2739. Min Act: -0.1700

Data Index: 4443363 (Open Web Text)

Max Activating Token Index: 322

Text #3

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.2365. Min Act: -0.1700

Data Index: 8775841 (Open Web Text)

Max Activating Token Index: 706

Text #4

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.2294. Min Act: -0.1700

Data Index: 4574403 (Open Web Text)

Max Activating Token Index: 275

Text #5

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.2267. Min Act: -0.1700

Data Index: 8735090 (Open Web Text)

Max Activating Token Index: 940

Text #6

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.2027. Min Act: -0.1700

Data Index: 4329095 (Open Web Text)

Max Activating Token Index: 801

Text #7

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1961. Min Act: -0.1700

Data Index: 7742137 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1904. Min Act: -0.1700

Data Index: 6914945 (Open Web Text)

Max Activating Token Index: 809

Text #9

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1930. Min Act: -0.1700

Data Index: 6561922 (Open Web Text)

Max Activating Token Index: 923

Text #10

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1882. Min Act: -0.1700

Data Index: 5489784 (Open Web Text)

Max Activating Token Index: 210

Text #11

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1673. Min Act: -0.1700

Data Index: 7247438 (Open Web Text)

Max Activating Token Index: 922

Text #12

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1502. Min Act: -0.1700

Data Index: 5284956 (Open Web Text)

Max Activating Token Index: 524

Text #13

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1510. Min Act: -0.1700

Data Index: 8336370 (Open Web Text)

Max Activating Token Index: 804

Text #14

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1461. Min Act: -0.1700

Data Index: 5328021 (Open Web Text)

Max Activating Token Index: 538

Text #15

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1334. Min Act: -0.1700

Data Index: 6804070 (Open Web Text)

Max Activating Token Index: 749

Text #16

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1065. Min Act: -0.1700

Data Index: 8799493 (Open Web Text)

Max Activating Token Index: 964

Text #17

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1223. Min Act: -0.1700

Data Index: 6348749 (Open Web Text)

Max Activating Token Index: 51

Text #18

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1233. Min Act: -0.1700

Data Index: 7560734 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 3.3110. Min Range: -3.3110

Max Act: 3.1098. Min Act: -0.1700

Data Index: 3169431 (Open Web Text)

Max Activating Token Index: 353