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

Dataset: Open Web Text

Neuron 1067 in Layer 0

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: 4.2803. Min Range: -4.2803

Max Act: 4.2803. Min Act: -0.1700

Data Index: 7513092 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2517. Min Act: -0.1700

Data Index: 4655194 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2591. Min Act: -0.1700

Data Index: 822457 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2450. Min Act: -0.1700

Data Index: 8449441 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2305. Min Act: -0.1700

Data Index: 8090213 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2531. Min Act: -0.1700

Data Index: 4590806 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2503. Min Act: -0.1700

Data Index: 5132084 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2352. Min Act: -0.1700

Data Index: 7108394 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2434. Min Act: -0.1700

Data Index: 7001875 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.1929. Min Act: -0.1700

Data Index: 6258397 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.1966. Min Act: -0.1700

Data Index: 8523908 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.1938. Min Act: -0.1700

Data Index: 7543071 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2166. Min Act: -0.1700

Data Index: 7401631 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2041. Min Act: -0.1700

Data Index: 6290238 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2078. Min Act: -0.1700

Data Index: 1429305 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2011. Min Act: -0.1700

Data Index: 2059667 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2183. Min Act: -0.1700

Data Index: 3935199 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.1967. Min Act: -0.1700

Data Index: 3907889 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2212. Min Act: -0.1700

Data Index: 3406457 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.2803. Min Range: -4.2803

Max Act: 4.2243. Min Act: -0.1700

Data Index: 3356760 (Open Web Text)

Max Activating Token Index: 6