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

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

Neuron 1661 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.6489. Min Act: -0.1700

Data Index: 242656 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.3364. Min Act: -0.1700

Data Index: 1028633 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.2426. Min Act: -0.1700

Data Index: 1283548 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.2739. Min Act: -0.1700

Data Index: 607031 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.2739. Min Act: -0.1700

Data Index: 302533 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.2114. Min Act: -0.1640

Data Index: 75671 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.1801. Min Act: -0.1700

Data Index: 531899 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.2114. Min Act: -0.1700

Data Index: 279024 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.2426. Min Act: -0.1700

Data Index: 428334 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.2114. Min Act: -0.1700

Data Index: 1216042 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.1801. Min Act: -0.1700

Data Index: 583874 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.2114. Min Act: -0.1700

Data Index: 766685 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.1801. Min Act: -0.1700

Data Index: 350278 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.1801. Min Act: -0.1700

Data Index: 336535 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.1489. Min Act: -0.1700

Data Index: 1163777 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.1489. Min Act: -0.1700

Data Index: 630433 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.1489. Min Act: -0.1700

Data Index: 1319135 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.1176. Min Act: -0.1700

Data Index: 869474 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.0864. Min Act: -0.1700

Data Index: 763718 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 5.6489. Min Range: -5.6489

Max Act: 5.0551. Min Act: -0.1700

Data Index: 617875 (C4 (Web Text))

Max Activating Token Index: 599