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

Dataset: Open Web Text

Neuron 166 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: 4.5592. Min Range: -4.5592

Max Act: 4.5250. Min Act: -0.1700

Data Index: 4988712 (Open Web Text)

Max Activating Token Index: 543

Text #1

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.5435. Min Act: -0.1700

Data Index: 3144923 (Open Web Text)

Max Activating Token Index: 641

Text #2

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.5381. Min Act: -0.1700

Data Index: 2540971 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.5592. Min Act: -0.1700

Data Index: 4554107 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.5226. Min Act: -0.1700

Data Index: 3278187 (Open Web Text)

Max Activating Token Index: 130

Text #5

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4814. Min Act: -0.1700

Data Index: 8485345 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4578. Min Act: -0.1700

Data Index: 8466761 (Open Web Text)

Max Activating Token Index: 259

Text #7

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4698. Min Act: -0.1700

Data Index: 2656331 (Open Web Text)

Max Activating Token Index: 150

Text #8

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4976. Min Act: -0.1700

Data Index: 4000036 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4741. Min Act: -0.1700

Data Index: 5465827 (Open Web Text)

Max Activating Token Index: 457

Text #10

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4707. Min Act: -0.1700

Data Index: 8511976 (Open Web Text)

Max Activating Token Index: 370

Text #11

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4282. Min Act: -0.1700

Data Index: 6577885 (Open Web Text)

Max Activating Token Index: 134

Text #12

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4224. Min Act: -0.1700

Data Index: 949848 (Open Web Text)

Max Activating Token Index: 143

Text #13

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4777. Min Act: -0.1700

Data Index: 5221804 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4341. Min Act: -0.1700

Data Index: 4825857 (Open Web Text)

Max Activating Token Index: 464

Text #15

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.3881. Min Act: -0.1700

Data Index: 6332031 (Open Web Text)

Max Activating Token Index: 441

Text #16

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.3881. Min Act: -0.1700

Data Index: 7119075 (Open Web Text)

Max Activating Token Index: 775

Text #17

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4245. Min Act: -0.1700

Data Index: 7828106 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4482. Min Act: -0.1700

Data Index: 1948708 (Open Web Text)

Max Activating Token Index: 947

Text #19

Max Range: 4.5592. Min Range: -4.5592

Max Act: 4.4323. Min Act: -0.1700

Data Index: 8080013 (Open Web Text)

Max Activating Token Index: 183