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

Dataset: Open Web Text

Neuron 1969 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: 3.5103. Min Range: -3.5103

Max Act: 3.5103. Min Act: -0.1700

Data Index: 4796805 (Open Web Text)

Max Activating Token Index: 1012

Text #1

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4905. Min Act: -0.1700

Data Index: 7889100 (Open Web Text)

Max Activating Token Index: 116

Text #2

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4462. Min Act: -0.1700

Data Index: 1842639 (Open Web Text)

Max Activating Token Index: 803

Text #3

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4461. Min Act: -0.1700

Data Index: 8279270 (Open Web Text)

Max Activating Token Index: 941

Text #4

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4388. Min Act: -0.1700

Data Index: 5246667 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4586. Min Act: -0.1700

Data Index: 3079217 (Open Web Text)

Max Activating Token Index: 795

Text #6

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4315. Min Act: -0.1700

Data Index: 8786827 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4147. Min Act: -0.1700

Data Index: 1779595 (Open Web Text)

Max Activating Token Index: 794

Text #8

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4280. Min Act: -0.1700

Data Index: 758760 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4091. Min Act: -0.1700

Data Index: 2384317 (Open Web Text)

Max Activating Token Index: 598

Text #10

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4146. Min Act: -0.1700

Data Index: 6550951 (Open Web Text)

Max Activating Token Index: 289

Text #11

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3992. Min Act: -0.1700

Data Index: 6513895 (Open Web Text)

Max Activating Token Index: 632

Text #12

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4288. Min Act: -0.1700

Data Index: 5832923 (Open Web Text)

Max Activating Token Index: 804

Text #13

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4201. Min Act: -0.1700

Data Index: 3256522 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4093. Min Act: -0.1700

Data Index: 5567954 (Open Web Text)

Max Activating Token Index: 838

Text #15

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3951. Min Act: -0.1700

Data Index: 1915378 (Open Web Text)

Max Activating Token Index: 642

Text #16

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3965. Min Act: -0.1700

Data Index: 2725474 (Open Web Text)

Max Activating Token Index: 690

Text #17

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4050. Min Act: -0.1700

Data Index: 5788285 (Open Web Text)

Max Activating Token Index: 858

Text #18

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.3981. Min Act: -0.1700

Data Index: 2462842 (Open Web Text)

Max Activating Token Index: 650

Text #19

Max Range: 3.5103. Min Range: -3.5103

Max Act: 3.4118. Min Act: -0.1700

Data Index: 6558224 (Open Web Text)

Max Activating Token Index: 627