Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1020 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.4702. Min Act: -0.1700

Data Index: 19034 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.4075. Min Act: -0.1700

Data Index: 323653 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3761. Min Act: -0.1700

Data Index: 728751 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3447. Min Act: -0.1700

Data Index: 1298695 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3447. Min Act: -0.1700

Data Index: 197408 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3447. Min Act: -0.1700

Data Index: 493288 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3447. Min Act: -0.1700

Data Index: 387191 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3133. Min Act: -0.1700

Data Index: 1282552 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3133. Min Act: -0.1700

Data Index: 944095 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3133. Min Act: -0.1700

Data Index: 1049529 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3133. Min Act: -0.1700

Data Index: 1074293 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3133. Min Act: -0.1700

Data Index: 53662 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3133. Min Act: -0.1700

Data Index: 1174049 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.3133. Min Act: -0.1700

Data Index: 1119266 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.2662. Min Act: -0.1700

Data Index: 486248 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.2819. Min Act: -0.1700

Data Index: 512820 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.2819. Min Act: -0.1700

Data Index: 411510 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1095391 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.2819. Min Act: -0.1700

Data Index: 863743 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 3.4702. Min Range: -3.4702

Max Act: 3.2819. Min Act: -0.1700

Data Index: 146931 (C4 (Web Text))

Max Activating Token Index: 866