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

Dataset: Open Web Text

Neuron 2304 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: 4.0191. Min Range: -4.0191

Max Act: 4.0191. Min Act: -0.1700

Data Index: 2297884 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9737. Min Act: -0.1700

Data Index: 5771032 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9860. Min Act: -0.1700

Data Index: 8184916 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9955. Min Act: -0.1700

Data Index: 6656995 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9422. Min Act: -0.1700

Data Index: 7478397 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9654. Min Act: -0.1700

Data Index: 6933637 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9193. Min Act: -0.1700

Data Index: 3433060 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9089. Min Act: -0.1700

Data Index: 6639401 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9192. Min Act: -0.1700

Data Index: 6379169 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9020. Min Act: -0.1700

Data Index: 6177024 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9213. Min Act: -0.1700

Data Index: 4415029 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.8965. Min Act: -0.1700

Data Index: 8069262 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.9078. Min Act: -0.1700

Data Index: 1162850 (Open Web Text)

Max Activating Token Index: 134

Text #13

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.8678. Min Act: -0.1700

Data Index: 4593229 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.8945. Min Act: -0.1700

Data Index: 6098601 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.8732. Min Act: -0.1700

Data Index: 456069 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.8692. Min Act: -0.1700

Data Index: 5785547 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.8654. Min Act: -0.1700

Data Index: 6687504 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.8763. Min Act: -0.1700

Data Index: 5009848 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.0191. Min Range: -4.0191

Max Act: 3.8948. Min Act: -0.1700

Data Index: 5016972 (Open Web Text)

Max Activating Token Index: 5