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

Dataset: Open Web Text

Neuron 1297 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: 3.0321. Min Range: -3.0321

Max Act: 3.0321. Min Act: -0.1700

Data Index: 825840 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.9066. Min Act: -0.1700

Data Index: 3261538 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8709. Min Act: -0.1700

Data Index: 3567691 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8881. Min Act: -0.1700

Data Index: 6261040 (Open Web Text)

Max Activating Token Index: 649

Text #4

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8374. Min Act: -0.1700

Data Index: 105090 (Open Web Text)

Max Activating Token Index: 273

Text #5

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8384. Min Act: -0.1700

Data Index: 3523848 (Open Web Text)

Max Activating Token Index: 295

Text #6

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8399. Min Act: -0.1700

Data Index: 2510819 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8091. Min Act: -0.1700

Data Index: 8160751 (Open Web Text)

Max Activating Token Index: 316

Text #8

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8280. Min Act: -0.1700

Data Index: 8798739 (Open Web Text)

Max Activating Token Index: 235

Text #9

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8240. Min Act: -0.1700

Data Index: 8480974 (Open Web Text)

Max Activating Token Index: 430

Text #10

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8103. Min Act: -0.1700

Data Index: 6756117 (Open Web Text)

Max Activating Token Index: 622

Text #11

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8106. Min Act: -0.1700

Data Index: 412134 (Open Web Text)

Max Activating Token Index: 898

Text #12

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8093. Min Act: -0.1700

Data Index: 1980403 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8192. Min Act: -0.1700

Data Index: 3644211 (Open Web Text)

Max Activating Token Index: 505

Text #14

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8020. Min Act: -0.1700

Data Index: 4296831 (Open Web Text)

Max Activating Token Index: 616

Text #15

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.7865. Min Act: -0.1700

Data Index: 5509572 (Open Web Text)

Max Activating Token Index: 289

Text #16

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8132. Min Act: -0.1700

Data Index: 4499821 (Open Web Text)

Max Activating Token Index: 920

Text #17

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.8017. Min Act: -0.1700

Data Index: 2910209 (Open Web Text)

Max Activating Token Index: 499

Text #18

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.7929. Min Act: -0.1700

Data Index: 2187458 (Open Web Text)

Max Activating Token Index: 509

Text #19

Max Range: 3.0321. Min Range: -3.0321

Max Act: 2.7958. Min Act: -0.1700

Data Index: 1081811 (Open Web Text)

Max Activating Token Index: 186