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

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

Neuron 1421 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: 3.1787. Min Range: -3.1787

Max Act: 3.1787. Min Act: -0.1700

Data Index: 571590 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 3.1787. Min Range: -3.1787

Max Act: 3.1612. Min Act: -0.1700

Data Index: 750785 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 3.1787. Min Range: -3.1787

Max Act: 3.1072. Min Act: -0.1700

Data Index: 669265 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 3.1787. Min Range: -3.1787

Max Act: 3.0763. Min Act: -0.1700

Data Index: 697629 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 3.1787. Min Range: -3.1787

Max Act: 3.0884. Min Act: -0.1700

Data Index: 983440 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 3.1787. Min Range: -3.1787

Max Act: 3.0425. Min Act: -0.1700

Data Index: 806230 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 3.1787. Min Range: -3.1787

Max Act: 3.0428. Min Act: -0.1700

Data Index: 1088815 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 3.1787. Min Range: -3.1787

Max Act: 3.0316. Min Act: -0.1700

Data Index: 1039663 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.1787. Min Range: -3.1787

Max Act: 3.0312. Min Act: -0.1700

Data Index: 784416 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 3.1787. Min Range: -3.1787

Max Act: 3.0265. Min Act: -0.1700

Data Index: 604052 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9983. Min Act: -0.1700

Data Index: 1342649 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9930. Min Act: -0.1700

Data Index: 1316266 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9965. Min Act: -0.1700

Data Index: 46074 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9516. Min Act: -0.1700

Data Index: 779050 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9695. Min Act: -0.1700

Data Index: 708292 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9736. Min Act: -0.1700

Data Index: 780815 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9793. Min Act: -0.1700

Data Index: 690092 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9596. Min Act: -0.1700

Data Index: 760893 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9766. Min Act: -0.1700

Data Index: 906000 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 3.1787. Min Range: -3.1787

Max Act: 2.9638. Min Act: -0.1700

Data Index: 448423 (C4 (Web Text))

Max Activating Token Index: 941