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

Dataset: Open Web Text

Neuron 1014 in Layer 3

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: 3.8980. Min Range: -3.8980

Max Act: 3.8980. Min Act: -0.1700

Data Index: 824284 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7633. Min Act: -0.1700

Data Index: 8827002 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7762. Min Act: -0.1700

Data Index: 1394292 (Open Web Text)

Max Activating Token Index: 401

Text #3

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7527. Min Act: -0.1700

Data Index: 1314310 (Open Web Text)

Max Activating Token Index: 780

Text #4

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.7013. Min Act: -0.1700

Data Index: 2065233 (Open Web Text)

Max Activating Token Index: 872

Text #5

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6824. Min Act: -0.1700

Data Index: 3365774 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6634. Min Act: -0.1700

Data Index: 6810669 (Open Web Text)

Max Activating Token Index: 484

Text #7

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6365. Min Act: -0.1700

Data Index: 1569106 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6165. Min Act: -0.1700

Data Index: 4626433 (Open Web Text)

Max Activating Token Index: 889

Text #9

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6186. Min Act: -0.1700

Data Index: 790475 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6435. Min Act: -0.1700

Data Index: 896994 (Open Web Text)

Max Activating Token Index: 409

Text #11

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6258. Min Act: -0.1700

Data Index: 6993346 (Open Web Text)

Max Activating Token Index: 204

Text #12

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6554. Min Act: -0.1700

Data Index: 3643503 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6069. Min Act: -0.1700

Data Index: 8773689 (Open Web Text)

Max Activating Token Index: 131

Text #14

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6227. Min Act: -0.1700

Data Index: 4185849 (Open Web Text)

Max Activating Token Index: 176

Text #15

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6257. Min Act: -0.1700

Data Index: 2763083 (Open Web Text)

Max Activating Token Index: 326

Text #16

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6505. Min Act: -0.1700

Data Index: 2311425 (Open Web Text)

Max Activating Token Index: 517

Text #17

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.5987. Min Act: -0.1700

Data Index: 4123984 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.5888. Min Act: -0.1700

Data Index: 4559832 (Open Web Text)

Max Activating Token Index: 881

Text #19

Max Range: 3.8980. Min Range: -3.8980

Max Act: 3.6087. Min Act: -0.1700

Data Index: 1157909 (Open Web Text)

Max Activating Token Index: 683