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

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

Neuron 1340 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: 3.6060. Min Range: -3.6060

Max Act: 3.6060. Min Act: -0.1700

Data Index: 908569 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.5277. Min Act: -0.1700

Data Index: 512637 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.5120. Min Act: -0.1700

Data Index: 1259156 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.3866. Min Act: -0.1700

Data Index: 763741 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.3552. Min Act: -0.1700

Data Index: 55129 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.3552. Min Act: -0.1700

Data Index: 1081112 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.3395. Min Act: -0.1700

Data Index: 500703 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2767. Min Act: -0.1700

Data Index: 571771 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2295. Min Act: -0.1700

Data Index: 895138 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2924. Min Act: -0.1700

Data Index: 1075671 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.3395. Min Act: -0.1700

Data Index: 404975 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2924. Min Act: -0.1700

Data Index: 340654 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2767. Min Act: -0.1700

Data Index: 1110363 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.3238. Min Act: -0.1700

Data Index: 743309 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2610. Min Act: -0.1700

Data Index: 1193672 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2295. Min Act: -0.1700

Data Index: 462441 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.3081. Min Act: -0.1700

Data Index: 251606 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.1824. Min Act: -0.1700

Data Index: 136673 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.1666. Min Act: -0.1700

Data Index: 738066 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 3.6060. Min Range: -3.6060

Max Act: 3.2295. Min Act: -0.1700

Data Index: 422225 (C4 (Web Text))

Max Activating Token Index: 971