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

Dataset: Open Web Text

Neuron 1131 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: 5.0342. Min Range: -5.0342

Max Act: 5.0342. Min Act: -0.1700

Data Index: 7912936 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 5.0342. Min Range: -5.0342

Max Act: 5.0021. Min Act: -0.1700

Data Index: 5841624 (Open Web Text)

Max Activating Token Index: 791

Text #2

Max Range: 5.0342. Min Range: -5.0342

Max Act: 5.0063. Min Act: -0.1700

Data Index: 5302054 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9904. Min Act: -0.1700

Data Index: 3030577 (Open Web Text)

Max Activating Token Index: 834

Text #4

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9499. Min Act: -0.1700

Data Index: 7485194 (Open Web Text)

Max Activating Token Index: 807

Text #5

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9532. Min Act: -0.1700

Data Index: 6687392 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9853. Min Act: -0.1700

Data Index: 8680577 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9412. Min Act: -0.1700

Data Index: 5148852 (Open Web Text)

Max Activating Token Index: 351

Text #8

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9333. Min Act: -0.1700

Data Index: 2776448 (Open Web Text)

Max Activating Token Index: 287

Text #9

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9203. Min Act: -0.1700

Data Index: 3606895 (Open Web Text)

Max Activating Token Index: 717

Text #10

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9471. Min Act: -0.1700

Data Index: 8106151 (Open Web Text)

Max Activating Token Index: 196

Text #11

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9686. Min Act: -0.1700

Data Index: 3663123 (Open Web Text)

Max Activating Token Index: 171

Text #12

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9567. Min Act: -0.1700

Data Index: 3378025 (Open Web Text)

Max Activating Token Index: 585

Text #13

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9022. Min Act: -0.1700

Data Index: 5587374 (Open Web Text)

Max Activating Token Index: 987

Text #14

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9154. Min Act: -0.1700

Data Index: 1155292 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.9148. Min Act: -0.1700

Data Index: 2402327 (Open Web Text)

Max Activating Token Index: 214

Text #16

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.8983. Min Act: -0.1700

Data Index: 6942542 (Open Web Text)

Max Activating Token Index: 631

Text #17

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.8875. Min Act: -0.1700

Data Index: 5983808 (Open Web Text)

Max Activating Token Index: 581

Text #18

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.8891. Min Act: -0.1700

Data Index: 6755595 (Open Web Text)

Max Activating Token Index: 955

Text #19

Max Range: 5.0342. Min Range: -5.0342

Max Act: 4.8650. Min Act: -0.1700

Data Index: 2021777 (Open Web Text)

Max Activating Token Index: 79