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

Dataset: Open Web Text

Neuron 1103 in Layer 5

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: 4.5622. Min Range: -4.5622

Max Act: 4.5622. Min Act: -0.1700

Data Index: 4945194 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.4408. Min Act: -0.1700

Data Index: 7398167 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.2459. Min Act: -0.1700

Data Index: 5008894 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.2754. Min Act: -0.1700

Data Index: 1828858 (Open Web Text)

Max Activating Token Index: 472

Text #4

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.2160. Min Act: -0.1700

Data Index: 8427540 (Open Web Text)

Max Activating Token Index: 812

Text #5

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.1638. Min Act: -0.1700

Data Index: 297912 (Open Web Text)

Max Activating Token Index: 553

Text #6

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.1485. Min Act: -0.1700

Data Index: 101258 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.1149. Min Act: -0.1700

Data Index: 3330021 (Open Web Text)

Max Activating Token Index: 279

Text #8

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.1524. Min Act: -0.1700

Data Index: 3519651 (Open Web Text)

Max Activating Token Index: 953

Text #9

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.1223. Min Act: -0.1700

Data Index: 4899180 (Open Web Text)

Max Activating Token Index: 815

Text #10

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.0942. Min Act: -0.1700

Data Index: 4231128 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.1131. Min Act: -0.1700

Data Index: 8455101 (Open Web Text)

Max Activating Token Index: 68

Text #12

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.0340. Min Act: -0.1700

Data Index: 1296733 (Open Web Text)

Max Activating Token Index: 304

Text #13

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.0423. Min Act: -0.1700

Data Index: 231961 (Open Web Text)

Max Activating Token Index: 762

Text #14

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.0528. Min Act: -0.1700

Data Index: 7948262 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.0549. Min Act: -0.1700

Data Index: 8282619 (Open Web Text)

Max Activating Token Index: 855

Text #16

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.0272. Min Act: -0.1700

Data Index: 4815652 (Open Web Text)

Max Activating Token Index: 437

Text #17

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.0398. Min Act: -0.1700

Data Index: 1893748 (Open Web Text)

Max Activating Token Index: 866

Text #18

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.0104. Min Act: -0.1700

Data Index: 7525288 (Open Web Text)

Max Activating Token Index: 186

Text #19

Max Range: 4.5622. Min Range: -4.5622

Max Act: 4.0221. Min Act: -0.1700

Data Index: 1658417 (Open Web Text)

Max Activating Token Index: 932