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

Dataset: Open Web Text

Neuron 1816 in Layer 0

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: 2.9154. Min Range: -2.9154

Max Act: 2.9098. Min Act: -0.1700

Data Index: 335258 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.9154. Min Act: -0.1700

Data Index: 1295726 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.9098. Min Act: -0.1700

Data Index: 2436866 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8681. Min Act: -0.1700

Data Index: 5257450 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8725. Min Act: -0.1700

Data Index: 6046312 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8753. Min Act: -0.1700

Data Index: 8382709 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8761. Min Act: -0.1700

Data Index: 2790226 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8675. Min Act: -0.1700

Data Index: 2422994 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8584. Min Act: -0.1700

Data Index: 178811 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8544. Min Act: -0.1700

Data Index: 3433584 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8570. Min Act: -0.1700

Data Index: 794776 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8612. Min Act: -0.1700

Data Index: 8161726 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8588. Min Act: -0.1700

Data Index: 6206495 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8613. Min Act: -0.1700

Data Index: 54730 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8581. Min Act: -0.1700

Data Index: 1877675 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8546. Min Act: -0.1700

Data Index: 3953278 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8408. Min Act: -0.1700

Data Index: 4334222 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8470. Min Act: -0.1700

Data Index: 63194 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8299. Min Act: -0.1700

Data Index: 2803090 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9154. Min Range: -2.9154

Max Act: 2.8200. Min Act: -0.1700

Data Index: 3566015 (Open Web Text)

Max Activating Token Index: 3