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

Dataset: Open Web Text

Neuron 453 in Layer 3

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: 5.8942. Min Range: -5.8942

Max Act: 5.8942. Min Act: -0.1700

Data Index: 621551 (Open Web Text)

Max Activating Token Index: 972

Text #1

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.8175. Min Act: -0.1699

Data Index: 94109 (Open Web Text)

Max Activating Token Index: 31

Text #2

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.8395. Min Act: -0.1700

Data Index: 2721997 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.7552. Min Act: -0.1699

Data Index: 4020377 (Open Web Text)

Max Activating Token Index: 1002

Text #4

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.7958. Min Act: -0.1700

Data Index: 1473049 (Open Web Text)

Max Activating Token Index: 88

Text #5

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.6967. Min Act: -0.1700

Data Index: 3899040 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.7658. Min Act: -0.1700

Data Index: 3952218 (Open Web Text)

Max Activating Token Index: 110

Text #7

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.7118. Min Act: -0.1700

Data Index: 7929165 (Open Web Text)

Max Activating Token Index: 36

Text #8

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.6641. Min Act: -0.1700

Data Index: 8273118 (Open Web Text)

Max Activating Token Index: 57

Text #9

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.6657. Min Act: -0.1698

Data Index: 6389372 (Open Web Text)

Max Activating Token Index: 618

Text #10

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.6588. Min Act: -0.1700

Data Index: 7298088 (Open Web Text)

Max Activating Token Index: 260

Text #11

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.6612. Min Act: -0.1700

Data Index: 7494928 (Open Web Text)

Max Activating Token Index: 402

Text #12

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.6452. Min Act: -0.1699

Data Index: 8090328 (Open Web Text)

Max Activating Token Index: 709

Text #13

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.5854. Min Act: -0.1700

Data Index: 6062046 (Open Web Text)

Max Activating Token Index: 538

Text #14

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.6122. Min Act: -0.1700

Data Index: 3227775 (Open Web Text)

Max Activating Token Index: 65

Text #15

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.6293. Min Act: -0.1698

Data Index: 4119131 (Open Web Text)

Max Activating Token Index: 369

Text #16

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.5325. Min Act: -0.1700

Data Index: 336638 (Open Web Text)

Max Activating Token Index: 114

Text #17

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.5431. Min Act: -0.1700

Data Index: 3358195 (Open Web Text)

Max Activating Token Index: 174

Text #18

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.6359. Min Act: -0.1700

Data Index: 6337070 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 5.8942. Min Range: -5.8942

Max Act: 5.5184. Min Act: -0.1700

Data Index: 6571017 (Open Web Text)

Max Activating Token Index: 599