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

Dataset: Open Web Text

Neuron 2961 in Layer 0

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: 5.5372. Min Range: -5.5372

Max Act: 5.5372. Min Act: -0.1700

Data Index: 7328747 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.5255. Min Act: -0.1700

Data Index: 4874905 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4939. Min Act: -0.1700

Data Index: 761419 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4557. Min Act: -0.1700

Data Index: 429003 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4381. Min Act: -0.1700

Data Index: 2913570 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4494. Min Act: -0.1700

Data Index: 850117 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4065. Min Act: -0.1700

Data Index: 4892347 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4039. Min Act: -0.1700

Data Index: 1622874 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4461. Min Act: -0.1700

Data Index: 8693526 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.3800. Min Act: -0.1700

Data Index: 3192685 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.3894. Min Act: -0.1700

Data Index: 7696423 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4081. Min Act: -0.1700

Data Index: 1069225 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4097. Min Act: -0.1700

Data Index: 1212284 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.3776. Min Act: -0.1700

Data Index: 2465380 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.3821. Min Act: -0.1700

Data Index: 2446517 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.3992. Min Act: -0.1700

Data Index: 6536065 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.3873. Min Act: -0.1700

Data Index: 5653740 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.4169. Min Act: -0.1700

Data Index: 5251842 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.3675. Min Act: -0.1700

Data Index: 1084453 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 5.5372. Min Range: -5.5372

Max Act: 5.3784. Min Act: -0.1700

Data Index: 4698476 (Open Web Text)

Max Activating Token Index: 4