Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1370 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2134. Min Range: -3.2134

Max Act: 3.2134. Min Act: -0.1700

Data Index: 526172 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 3.2134. Min Range: -3.2134

Max Act: 3.1032. Min Act: -0.1700

Data Index: 446647 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 3.2134. Min Range: -3.2134

Max Act: 3.0874. Min Act: -0.1700

Data Index: 62758 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 3.2134. Min Range: -3.2134

Max Act: 3.0085. Min Act: -0.1700

Data Index: 719582 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 3.2134. Min Range: -3.2134

Max Act: 3.0559. Min Act: -0.1700

Data Index: 701621 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 3.2134. Min Range: -3.2134

Max Act: 3.0559. Min Act: -0.1700

Data Index: 323157 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 3.2134. Min Range: -3.2134

Max Act: 3.0401. Min Act: -0.1700

Data Index: 1004230 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9927. Min Act: -0.1700

Data Index: 380258 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 3.2134. Min Range: -3.2134

Max Act: 3.0085. Min Act: -0.1700

Data Index: 360651 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9927. Min Act: -0.1700

Data Index: 281478 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9610. Min Act: -0.1700

Data Index: 1193520 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9927. Min Act: -0.1700

Data Index: 910041 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9769. Min Act: -0.1700

Data Index: 1229061 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9769. Min Act: -0.1700

Data Index: 474681 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9769. Min Act: -0.1700

Data Index: 353374 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9769. Min Act: -0.1700

Data Index: 427391 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9610. Min Act: -0.1700

Data Index: 1046808 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9452. Min Act: -0.1700

Data Index: 232620 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9452. Min Act: -0.1700

Data Index: 1028225 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 3.2134. Min Range: -3.2134

Max Act: 2.9610. Min Act: -0.1700

Data Index: 854129 (C4 (Web Text))

Max Activating Token Index: 859