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

Dataset: Open Web Text

Neuron 2681 in Layer 6

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: 3.9161. Min Range: -3.9161

Max Act: 3.9161. Min Act: -0.1700

Data Index: 6941617 (Open Web Text)

Max Activating Token Index: 218

Text #1

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.9116. Min Act: -0.1700

Data Index: 3514577 (Open Web Text)

Max Activating Token Index: 810

Text #2

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.8120. Min Act: -0.1700

Data Index: 6811784 (Open Web Text)

Max Activating Token Index: 95

Text #3

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.8214. Min Act: -0.1700

Data Index: 923090 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.8165. Min Act: -0.1700

Data Index: 5173937 (Open Web Text)

Max Activating Token Index: 912

Text #5

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.7379. Min Act: -0.1700

Data Index: 6363873 (Open Web Text)

Max Activating Token Index: 641

Text #6

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.7112. Min Act: -0.1700

Data Index: 630553 (Open Web Text)

Max Activating Token Index: 755

Text #7

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.7213. Min Act: -0.1700

Data Index: 6739223 (Open Web Text)

Max Activating Token Index: 259

Text #8

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.7067. Min Act: -0.1700

Data Index: 4470680 (Open Web Text)

Max Activating Token Index: 140

Text #9

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.7290. Min Act: -0.1700

Data Index: 56899 (Open Web Text)

Max Activating Token Index: 51

Text #10

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.6898. Min Act: -0.1700

Data Index: 5495311 (Open Web Text)

Max Activating Token Index: 711

Text #11

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.6554. Min Act: -0.1700

Data Index: 3800158 (Open Web Text)

Max Activating Token Index: 589

Text #12

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.6591. Min Act: -0.1700

Data Index: 4371680 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.6002. Min Act: -0.1700

Data Index: 6885291 (Open Web Text)

Max Activating Token Index: 696

Text #14

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.6028. Min Act: -0.1700

Data Index: 2464764 (Open Web Text)

Max Activating Token Index: 124

Text #15

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.5942. Min Act: -0.1700

Data Index: 5034385 (Open Web Text)

Max Activating Token Index: 757

Text #16

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.5900. Min Act: -0.1700

Data Index: 6070273 (Open Web Text)

Max Activating Token Index: 951

Text #17

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.6050. Min Act: -0.1700

Data Index: 7880975 (Open Web Text)

Max Activating Token Index: 954

Text #18

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.5624. Min Act: -0.1700

Data Index: 7064558 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 3.9161. Min Range: -3.9161

Max Act: 3.5655. Min Act: -0.1700

Data Index: 2526143 (Open Web Text)

Max Activating Token Index: 437