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

Dataset: Open Web Text

Neuron 2860 in Layer 1

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: 3.5895. Min Range: -3.5895

Max Act: 3.5895. Min Act: -0.1700

Data Index: 8831531 (Open Web Text)

Max Activating Token Index: 905

Text #1

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.5702. Min Act: -0.1700

Data Index: 3523925 (Open Web Text)

Max Activating Token Index: 663

Text #2

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.5579. Min Act: -0.1700

Data Index: 5589422 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.5212. Min Act: -0.1700

Data Index: 1448158 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.5262. Min Act: -0.1700

Data Index: 4424918 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.5213. Min Act: -0.1700

Data Index: 8805408 (Open Web Text)

Max Activating Token Index: 227

Text #6

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4951. Min Act: -0.1700

Data Index: 3292814 (Open Web Text)

Max Activating Token Index: 419

Text #7

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4981. Min Act: -0.1700

Data Index: 1226548 (Open Web Text)

Max Activating Token Index: 317

Text #8

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4956. Min Act: -0.1700

Data Index: 6355378 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4965. Min Act: -0.1700

Data Index: 5191313 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4956. Min Act: -0.1700

Data Index: 1903269 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4723. Min Act: -0.1700

Data Index: 4855879 (Open Web Text)

Max Activating Token Index: 349

Text #12

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4736. Min Act: -0.1700

Data Index: 7512127 (Open Web Text)

Max Activating Token Index: 850

Text #13

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4418. Min Act: -0.1700

Data Index: 4287363 (Open Web Text)

Max Activating Token Index: 942

Text #14

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4431. Min Act: -0.1700

Data Index: 3902603 (Open Web Text)

Max Activating Token Index: 267

Text #15

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4446. Min Act: -0.1700

Data Index: 1396515 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4338. Min Act: -0.1700

Data Index: 894854 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4382. Min Act: -0.1700

Data Index: 6490894 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4376. Min Act: -0.1700

Data Index: 3915197 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 3.5895. Min Range: -3.5895

Max Act: 3.4183. Min Act: -0.1700

Data Index: 6976662 (Open Web Text)

Max Activating Token Index: 782