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

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

Neuron 962 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.9545. Min Act: -0.1700

Data Index: 1342931 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.9545. Min Act: -0.1700

Data Index: 968914 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.9069. Min Act: -0.1700

Data Index: 763055 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8752. Min Act: -0.1700

Data Index: 947681 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8434. Min Act: -0.1700

Data Index: 601833 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.8116. Min Act: -0.1700

Data Index: 176043 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7957. Min Act: -0.1700

Data Index: 26204 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7957. Min Act: -0.1700

Data Index: 682648 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7957. Min Act: -0.1700

Data Index: 1191894 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7798. Min Act: -0.1700

Data Index: 41018 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7798. Min Act: -0.1700

Data Index: 788349 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7638. Min Act: -0.1700

Data Index: 1077404 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7638. Min Act: -0.1700

Data Index: 1237677 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7798. Min Act: -0.1700

Data Index: 242837 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7319. Min Act: -0.1700

Data Index: 1256686 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7638. Min Act: -0.1700

Data Index: 1283949 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7479. Min Act: -0.1700

Data Index: 183103 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7319. Min Act: -0.1700

Data Index: 198396 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7479. Min Act: -0.1700

Data Index: 546349 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 2.9545. Min Range: -2.9545

Max Act: 2.7319. Min Act: -0.1700

Data Index: 453487 (C4 (Web Text))

Max Activating Token Index: 559