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

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

Neuron 607 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.5800. Min Act: -0.1700

Data Index: 731379 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.5957. Min Act: -0.1699

Data Index: 790595 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.5017. Min Act: -0.1700

Data Index: 832120 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.5017. Min Act: -0.1699

Data Index: 26088 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.5173. Min Act: -0.1700

Data Index: 466550 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.5330. Min Act: -0.1700

Data Index: 179331 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.5017. Min Act: -0.1700

Data Index: 1094704 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4860. Min Act: -0.1700

Data Index: 444559 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4703. Min Act: -0.1700

Data Index: 94268 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4547. Min Act: -0.1700

Data Index: 414550 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4703. Min Act: -0.1700

Data Index: 377631 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4703. Min Act: -0.1700

Data Index: 287168 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4390. Min Act: -0.1700

Data Index: 676635 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4547. Min Act: -0.1700

Data Index: 204128 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4390. Min Act: -0.1700

Data Index: 324114 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4547. Min Act: -0.1700

Data Index: 757587 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4233. Min Act: -0.1700

Data Index: 1602528 (Python Code)

Max Activating Token Index: 916

Text #17

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4233. Min Act: -0.1700

Data Index: 849378 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4390. Min Act: -0.1700

Data Index: 1008695 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 3.5957. Min Range: -3.5957

Max Act: 3.4233. Min Act: -0.1699

Data Index: 495787 (C4 (Web Text))

Max Activating Token Index: 395