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

Dataset: Open Web Text

Neuron 688 in Layer 3

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: 3.0209. Min Range: -3.0209

Max Act: 3.0209. Min Act: -0.1700

Data Index: 309352 (Open Web Text)

Max Activating Token Index: 782

Text #1

Max Range: 3.0209. Min Range: -3.0209

Max Act: 3.0159. Min Act: -0.1700

Data Index: 7687298 (Open Web Text)

Max Activating Token Index: 1013

Text #2

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9933. Min Act: -0.1700

Data Index: 734489 (Open Web Text)

Max Activating Token Index: 354

Text #3

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9834. Min Act: -0.1700

Data Index: 723767 (Open Web Text)

Max Activating Token Index: 512

Text #4

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9577. Min Act: -0.1700

Data Index: 94422 (Open Web Text)

Max Activating Token Index: 352

Text #5

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9669. Min Act: -0.1700

Data Index: 6359045 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9631. Min Act: -0.1700

Data Index: 6117437 (Open Web Text)

Max Activating Token Index: 289

Text #7

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9642. Min Act: -0.1700

Data Index: 6165879 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9608. Min Act: -0.1700

Data Index: 2521728 (Open Web Text)

Max Activating Token Index: 57

Text #9

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9570. Min Act: -0.1700

Data Index: 7609141 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9524. Min Act: -0.1700

Data Index: 7291739 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9470. Min Act: -0.1700

Data Index: 3346415 (Open Web Text)

Max Activating Token Index: 820

Text #12

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9333. Min Act: -0.1700

Data Index: 1072664 (Open Web Text)

Max Activating Token Index: 397

Text #13

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9463. Min Act: -0.1700

Data Index: 7249636 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9310. Min Act: -0.1700

Data Index: 6460252 (Open Web Text)

Max Activating Token Index: 827

Text #15

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9368. Min Act: -0.1700

Data Index: 295084 (Open Web Text)

Max Activating Token Index: 362

Text #16

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9253. Min Act: -0.1700

Data Index: 5657625 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9142. Min Act: -0.1700

Data Index: 1221084 (Open Web Text)

Max Activating Token Index: 476

Text #18

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9163. Min Act: -0.1700

Data Index: 6550095 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 3.0209. Min Range: -3.0209

Max Act: 2.9229. Min Act: -0.1700

Data Index: 644778 (Open Web Text)

Max Activating Token Index: 284