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

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

Neuron 1878 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: 3.2333. Min Range: -3.2333

Max Act: 3.2333. Min Act: -0.1699

Data Index: 828772 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.2080. Min Act: -0.1700

Data Index: 253310 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.1050. Min Act: -0.1700

Data Index: 276285 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0945. Min Act: -0.1700

Data Index: 349660 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0822. Min Act: -0.1700

Data Index: 410912 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0651. Min Act: -0.1700

Data Index: 347729 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0641. Min Act: -0.1699

Data Index: 33557 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0626. Min Act: -0.1700

Data Index: 1215114 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0366. Min Act: -0.1700

Data Index: 1006805 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0264. Min Act: -0.1700

Data Index: 572954 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0137. Min Act: -0.1700

Data Index: 745181 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0311. Min Act: -0.1700

Data Index: 96119 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0067. Min Act: -0.1700

Data Index: 45269 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 3.2333. Min Range: -3.2333

Max Act: 3.0054. Min Act: -0.1700

Data Index: 374678 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 3.2333. Min Range: -3.2333

Max Act: 2.9916. Min Act: -0.1700

Data Index: 773988 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 3.2333. Min Range: -3.2333

Max Act: 2.9874. Min Act: -0.1700

Data Index: 823409 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 3.2333. Min Range: -3.2333

Max Act: 2.9649. Min Act: -0.1700

Data Index: 78270 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 3.2333. Min Range: -3.2333

Max Act: 2.9640. Min Act: -0.1700

Data Index: 524802 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 3.2333. Min Range: -3.2333

Max Act: 2.9593. Min Act: -0.1700

Data Index: 717056 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 3.2333. Min Range: -3.2333

Max Act: 2.9631. Min Act: -0.1700

Data Index: 757362 (C4 (Web Text))

Max Activating Token Index: 465