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

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

Neuron 1105 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: 3.3683. Min Range: -3.3683

Max Act: 3.2741. Min Act: -0.1700

Data Index: 25736 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.3683. Min Act: -0.1700

Data Index: 851940 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2741. Min Act: -0.1700

Data Index: 1000559 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2741. Min Act: -0.1700

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2741. Min Act: -0.1700

Data Index: 389248 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2270. Min Act: -0.1700

Data Index: 228107 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.1955. Min Act: -0.1700

Data Index: 905385 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2427. Min Act: -0.1700

Data Index: 1089194 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2584. Min Act: -0.1700

Data Index: 1308564 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2427. Min Act: -0.1700

Data Index: 162478 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2113. Min Act: -0.1700

Data Index: 1355514 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.1955. Min Act: -0.1700

Data Index: 1056840 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2113. Min Act: -0.1700

Data Index: 1341943 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2270. Min Act: -0.1700

Data Index: 673215 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2270. Min Act: -0.1700

Data Index: 342796 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2270. Min Act: -0.1700

Data Index: 932672 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.1955. Min Act: -0.1700

Data Index: 300889 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2113. Min Act: -0.1700

Data Index: 1173229 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.2113. Min Act: -0.1700

Data Index: 709840 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 3.3683. Min Range: -3.3683

Max Act: 3.1955. Min Act: -0.1700

Data Index: 1208556 (C4 (Web Text))

Max Activating Token Index: 608