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

Dataset: Open Web Text

Neuron 1029 in Layer 6

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: 4.6058. Min Range: -4.6058

Max Act: 4.6058. Min Act: -0.1700

Data Index: 467907 (Open Web Text)

Max Activating Token Index: 460

Text #1

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4698. Min Act: -0.1700

Data Index: 8797549 (Open Web Text)

Max Activating Token Index: 934

Text #2

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4903. Min Act: -0.1700

Data Index: 2917810 (Open Web Text)

Max Activating Token Index: 838

Text #3

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4280. Min Act: -0.1700

Data Index: 7509948 (Open Web Text)

Max Activating Token Index: 780

Text #4

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4229. Min Act: -0.1700

Data Index: 7596341 (Open Web Text)

Max Activating Token Index: 631

Text #5

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4185. Min Act: -0.1700

Data Index: 7193611 (Open Web Text)

Max Activating Token Index: 560

Text #6

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4486. Min Act: -0.1700

Data Index: 2084583 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4557. Min Act: -0.1700

Data Index: 7980633 (Open Web Text)

Max Activating Token Index: 833

Text #8

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.4010. Min Act: -0.1700

Data Index: 8270753 (Open Web Text)

Max Activating Token Index: 922

Text #9

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3729. Min Act: -0.1700

Data Index: 5353052 (Open Web Text)

Max Activating Token Index: 299

Text #10

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3702. Min Act: -0.1700

Data Index: 3988016 (Open Web Text)

Max Activating Token Index: 389

Text #11

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3677. Min Act: -0.1700

Data Index: 1213687 (Open Web Text)

Max Activating Token Index: 727

Text #12

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3672. Min Act: -0.1700

Data Index: 993257 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3362. Min Act: -0.1700

Data Index: 7471064 (Open Web Text)

Max Activating Token Index: 277

Text #14

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3581. Min Act: -0.1700

Data Index: 4445442 (Open Web Text)

Max Activating Token Index: 259

Text #15

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3398. Min Act: -0.1700

Data Index: 2275578 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3138. Min Act: -0.1700

Data Index: 6975098 (Open Web Text)

Max Activating Token Index: 403

Text #17

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.2963. Min Act: -0.1700

Data Index: 6829531 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3170. Min Act: -0.1700

Data Index: 5492671 (Open Web Text)

Max Activating Token Index: 964

Text #19

Max Range: 4.6058. Min Range: -4.6058

Max Act: 4.3140. Min Act: -0.1700

Data Index: 2851853 (Open Web Text)

Max Activating Token Index: 709