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

Dataset: Open Web Text

Neuron 41 in Layer 2

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: 3.4887. Min Range: -3.4887

Max Act: 3.4507. Min Act: -0.1700

Data Index: 6163235 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4882. Min Act: -0.1700

Data Index: 8700620 (Open Web Text)

Max Activating Token Index: 795

Text #2

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4887. Min Act: -0.1700

Data Index: 3855444 (Open Web Text)

Max Activating Token Index: 192

Text #3

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4598. Min Act: -0.1700

Data Index: 5766951 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4432. Min Act: -0.1700

Data Index: 848470 (Open Web Text)

Max Activating Token Index: 980

Text #5

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4461. Min Act: -0.1700

Data Index: 2630656 (Open Web Text)

Max Activating Token Index: 135

Text #6

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4239. Min Act: -0.1700

Data Index: 4628876 (Open Web Text)

Max Activating Token Index: 614

Text #7

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4135. Min Act: -0.1700

Data Index: 7288759 (Open Web Text)

Max Activating Token Index: 996

Text #8

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4525. Min Act: -0.1700

Data Index: 4906238 (Open Web Text)

Max Activating Token Index: 613

Text #9

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4042. Min Act: -0.1700

Data Index: 4505085 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4588. Min Act: -0.1700

Data Index: 4191894 (Open Web Text)

Max Activating Token Index: 364

Text #11

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4318. Min Act: -0.1700

Data Index: 374991 (Open Web Text)

Max Activating Token Index: 170

Text #12

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4197. Min Act: -0.1700

Data Index: 3598459 (Open Web Text)

Max Activating Token Index: 598

Text #13

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.3967. Min Act: -0.1700

Data Index: 3311581 (Open Web Text)

Max Activating Token Index: 262

Text #14

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4000. Min Act: -0.1700

Data Index: 2196342 (Open Web Text)

Max Activating Token Index: 783

Text #15

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.3956. Min Act: -0.1700

Data Index: 6284581 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.3981. Min Act: -0.1700

Data Index: 1235700 (Open Web Text)

Max Activating Token Index: 367

Text #17

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.3811. Min Act: -0.1700

Data Index: 3620993 (Open Web Text)

Max Activating Token Index: 299

Text #18

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.3906. Min Act: -0.1700

Data Index: 121713 (Open Web Text)

Max Activating Token Index: 987

Text #19

Max Range: 3.4887. Min Range: -3.4887

Max Act: 3.4080. Min Act: -0.1700

Data Index: 4952457 (Open Web Text)

Max Activating Token Index: 388