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

Dataset: Open Web Text

Neuron 2357 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: 4.0943. Min Range: -4.0943

Max Act: 4.0874. Min Act: -0.1700

Data Index: 2035911 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0943. Min Act: -0.1700

Data Index: 3225511 (Open Web Text)

Max Activating Token Index: 310

Text #2

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0554. Min Act: -0.1700

Data Index: 2401905 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0716. Min Act: -0.1700

Data Index: 746225 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0525. Min Act: -0.1700

Data Index: 1446455 (Open Web Text)

Max Activating Token Index: 193

Text #5

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0029. Min Act: -0.1700

Data Index: 983535 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0213. Min Act: -0.1700

Data Index: 4290088 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0397. Min Act: -0.1700

Data Index: 1139828 (Open Web Text)

Max Activating Token Index: 333

Text #8

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9930. Min Act: -0.1700

Data Index: 2301324 (Open Web Text)

Max Activating Token Index: 967

Text #9

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0372. Min Act: -0.1700

Data Index: 7912578 (Open Web Text)

Max Activating Token Index: 932

Text #10

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0227. Min Act: -0.1700

Data Index: 2164241 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0247. Min Act: -0.1700

Data Index: 623249 (Open Web Text)

Max Activating Token Index: 168

Text #12

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0113. Min Act: -0.1700

Data Index: 3069192 (Open Web Text)

Max Activating Token Index: 171

Text #13

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0036. Min Act: -0.1700

Data Index: 5704529 (Open Web Text)

Max Activating Token Index: 836

Text #14

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0137. Min Act: -0.1700

Data Index: 5551434 (Open Web Text)

Max Activating Token Index: 575

Text #15

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0182. Min Act: -0.1700

Data Index: 5005001 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.0943. Min Range: -4.0943

Max Act: 4.0095. Min Act: -0.1700

Data Index: 4136977 (Open Web Text)

Max Activating Token Index: 537

Text #17

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9886. Min Act: -0.1700

Data Index: 3088967 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9600. Min Act: -0.1700

Data Index: 549119 (Open Web Text)

Max Activating Token Index: 606

Text #19

Max Range: 4.0943. Min Range: -4.0943

Max Act: 3.9780. Min Act: -0.1700

Data Index: 3688264 (Open Web Text)

Max Activating Token Index: 694