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

Dataset: Open Web Text

Neuron 3029 in Layer 2

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: 1.6685. Min Range: -1.6685

Max Act: 1.6685. Min Act: -0.1699

Data Index: 3206230 (Open Web Text)

Max Activating Token Index: 79

Text #1

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6281. Min Act: -0.1700

Data Index: 2859658 (Open Web Text)

Max Activating Token Index: 775

Text #2

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6415. Min Act: -0.1700

Data Index: 4284674 (Open Web Text)

Max Activating Token Index: 542

Text #3

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6301. Min Act: -0.1700

Data Index: 1392607 (Open Web Text)

Max Activating Token Index: 851

Text #4

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6340. Min Act: -0.1700

Data Index: 5604909 (Open Web Text)

Max Activating Token Index: 560

Text #5

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6356. Min Act: -0.1700

Data Index: 6501270 (Open Web Text)

Max Activating Token Index: 523

Text #6

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6119. Min Act: -0.1700

Data Index: 2516545 (Open Web Text)

Max Activating Token Index: 127

Text #7

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6175. Min Act: -0.1700

Data Index: 3807849 (Open Web Text)

Max Activating Token Index: 103

Text #8

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6190. Min Act: -0.1700

Data Index: 4524421 (Open Web Text)

Max Activating Token Index: 263

Text #9

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6254. Min Act: -0.1700

Data Index: 3569049 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6001. Min Act: -0.1700

Data Index: 2448506 (Open Web Text)

Max Activating Token Index: 125

Text #11

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6111. Min Act: -0.1700

Data Index: 2974404 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6091. Min Act: -0.1700

Data Index: 3189539 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5955. Min Act: -0.1700

Data Index: 5952118 (Open Web Text)

Max Activating Token Index: 363

Text #14

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6159. Min Act: -0.1700

Data Index: 6078302 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.6095. Min Act: -0.1700

Data Index: 3829038 (Open Web Text)

Max Activating Token Index: 44

Text #16

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5970. Min Act: -0.1700

Data Index: 5364701 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5937. Min Act: -0.1700

Data Index: 3981040 (Open Web Text)

Max Activating Token Index: 962

Text #18

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5913. Min Act: -0.1700

Data Index: 2876448 (Open Web Text)

Max Activating Token Index: 107

Text #19

Max Range: 1.6685. Min Range: -1.6685

Max Act: 1.5901. Min Act: -0.1700

Data Index: 1290900 (Open Web Text)

Max Activating Token Index: 121