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

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

Neuron 1340 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.6347. Min Act: -0.1700

Data Index: 1051937 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.5877. Min Act: -0.1700

Data Index: 627496 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.5877. Min Act: -0.1700

Data Index: 1144807 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.5720. Min Act: -0.1700

Data Index: 439269 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4937. Min Act: -0.1700

Data Index: 254083 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.5250. Min Act: -0.1700

Data Index: 1225103 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4937. Min Act: -0.1700

Data Index: 1583 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.5094. Min Act: -0.1700

Data Index: 840303 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4780. Min Act: -0.1700

Data Index: 810480 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4780. Min Act: -0.1700

Data Index: 960541 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4780. Min Act: -0.1700

Data Index: 1275932 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4780. Min Act: -0.1700

Data Index: 299864 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4780. Min Act: -0.1700

Data Index: 1177519 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4780. Min Act: -0.1700

Data Index: 141988 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4467. Min Act: -0.1700

Data Index: 788756 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4624. Min Act: -0.1700

Data Index: 369047 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4624. Min Act: -0.1700

Data Index: 1302112 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4624. Min Act: -0.1700

Data Index: 1318123 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4780. Min Act: -0.1700

Data Index: 906469 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 3.6347. Min Range: -3.6347

Max Act: 3.4624. Min Act: -0.1700

Data Index: 792826 (C4 (Web Text))

Max Activating Token Index: 362