Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1097 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.0980. Min Range: -5.0980

Max Act: 5.0980. Min Act: -0.1700

Data Index: 314755 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 5.0980. Min Range: -5.0980

Max Act: 5.0844. Min Act: -0.1700

Data Index: 1229917 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.8962. Min Act: -0.1700

Data Index: 728015 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.8987. Min Act: -0.1700

Data Index: 1129916 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.8317. Min Act: -0.1700

Data Index: 1069104 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.7715. Min Act: -0.1700

Data Index: 1164850 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.7842. Min Act: -0.1700

Data Index: 623013 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.6540. Min Act: -0.1700

Data Index: 698068 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.6303. Min Act: -0.1700

Data Index: 1057402 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.5571. Min Act: -0.1700

Data Index: 764923 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.6139. Min Act: -0.1700

Data Index: 437274 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.5661. Min Act: -0.1700

Data Index: 92836 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.5274. Min Act: -0.1700

Data Index: 125995 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.5533. Min Act: -0.1700

Data Index: 386154 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.4748. Min Act: -0.1700

Data Index: 73865 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.4619. Min Act: -0.1700

Data Index: 616038 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.4754. Min Act: -0.1700

Data Index: 1037342 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.4783. Min Act: -0.1700

Data Index: 287205 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.4339. Min Act: -0.1700

Data Index: 427618 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 5.0980. Min Range: -5.0980

Max Act: 4.4707. Min Act: -0.1700

Data Index: 22032 (C4 (Web Text))

Max Activating Token Index: 347