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

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

Neuron 795 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1137. Min Range: -5.1137

Max Act: 5.1137. Min Act: -0.1700

Data Index: 1133214 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 5.1137. Min Range: -5.1137

Max Act: 5.0512. Min Act: -0.1700

Data Index: 1352063 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 5.1137. Min Range: -5.1137

Max Act: 5.0825. Min Act: -0.1700

Data Index: 500600 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 5.1137. Min Range: -5.1137

Max Act: 5.0200. Min Act: -0.1700

Data Index: 630565 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 5.1137. Min Range: -5.1137

Max Act: 5.0512. Min Act: -0.1700

Data Index: 450889 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 5.1137. Min Range: -5.1137

Max Act: 5.0512. Min Act: -0.1700

Data Index: 153251 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 5.1137. Min Range: -5.1137

Max Act: 5.0200. Min Act: -0.1700

Data Index: 1182672 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.9887. Min Act: -0.1700

Data Index: 1210451 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 5.1137. Min Range: -5.1137

Max Act: 5.0200. Min Act: -0.1700

Data Index: 1150765 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.9887. Min Act: -0.1700

Data Index: 1055719 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.9575. Min Act: -0.1700

Data Index: 462943 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.9575. Min Act: -0.1700

Data Index: 524540 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 5.1137. Min Range: -5.1137

Max Act: 5.0200. Min Act: -0.1700

Data Index: 779146 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.9887. Min Act: -0.1700

Data Index: 440654 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.9262. Min Act: -0.1700

Data Index: 847407 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.9887. Min Act: -0.1700

Data Index: 15328 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.9262. Min Act: -0.1700

Data Index: 345754 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.8950. Min Act: -0.1700

Data Index: 839819 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.9887. Min Act: -0.1700

Data Index: 1201688 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 5.1137. Min Range: -5.1137

Max Act: 4.8950. Min Act: -0.1700

Data Index: 242233 (C4 (Web Text))

Max Activating Token Index: 577