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

Dataset: Open Web Text

Neuron 879 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: 3.5763. Min Range: -3.5763

Max Act: 3.5763. Min Act: -0.1700

Data Index: 1803285 (Open Web Text)

Max Activating Token Index: 496

Text #1

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.5408. Min Act: -0.1700

Data Index: 6332906 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.5085. Min Act: -0.1700

Data Index: 6070884 (Open Web Text)

Max Activating Token Index: 663

Text #3

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.5055. Min Act: -0.1700

Data Index: 3102338 (Open Web Text)

Max Activating Token Index: 487

Text #4

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4409. Min Act: -0.1700

Data Index: 6326860 (Open Web Text)

Max Activating Token Index: 745

Text #5

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4450. Min Act: -0.1700

Data Index: 7645524 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4646. Min Act: -0.1700

Data Index: 4487630 (Open Web Text)

Max Activating Token Index: 482

Text #7

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4177. Min Act: -0.1700

Data Index: 8453029 (Open Web Text)

Max Activating Token Index: 374

Text #8

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4101. Min Act: -0.1700

Data Index: 7256929 (Open Web Text)

Max Activating Token Index: 880

Text #9

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4118. Min Act: -0.1700

Data Index: 6019156 (Open Web Text)

Max Activating Token Index: 125

Text #10

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4399. Min Act: -0.1700

Data Index: 8310225 (Open Web Text)

Max Activating Token Index: 796

Text #11

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4074. Min Act: -0.1700

Data Index: 809383 (Open Web Text)

Max Activating Token Index: 229

Text #12

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.3921. Min Act: -0.1700

Data Index: 3595791 (Open Web Text)

Max Activating Token Index: 200

Text #13

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4043. Min Act: -0.1700

Data Index: 7946043 (Open Web Text)

Max Activating Token Index: 837

Text #14

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.3960. Min Act: -0.1700

Data Index: 7946045 (Open Web Text)

Max Activating Token Index: 660

Text #15

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.3961. Min Act: -0.1700

Data Index: 7760863 (Open Web Text)

Max Activating Token Index: 675

Text #16

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.3881. Min Act: -0.1700

Data Index: 7583406 (Open Web Text)

Max Activating Token Index: 891

Text #17

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.3870. Min Act: -0.1700

Data Index: 2068629 (Open Web Text)

Max Activating Token Index: 137

Text #18

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.4083. Min Act: -0.1700

Data Index: 733191 (Open Web Text)

Max Activating Token Index: 632

Text #19

Max Range: 3.5763. Min Range: -3.5763

Max Act: 3.3911. Min Act: -0.1700

Data Index: 4260892 (Open Web Text)

Max Activating Token Index: 890