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

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

Neuron 890 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.9086. Min Act: -0.1700

Data Index: 1058035 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.7836. Min Act: -0.1700

Data Index: 1089484 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.7836. Min Act: -0.1700

Data Index: 1001857 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.5336. Min Act: -0.1700

Data Index: 1079582 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.6274. Min Act: -0.1700

Data Index: 305440 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.5649. Min Act: -0.1700

Data Index: 10047 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.6274. Min Act: -0.1700

Data Index: 169701 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.5649. Min Act: -0.1700

Data Index: 825089 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.5336. Min Act: -0.1700

Data Index: 997599 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.5336. Min Act: -0.1700

Data Index: 483204 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.4711. Min Act: -0.1700

Data Index: 616509 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.4711. Min Act: -0.1700

Data Index: 182020 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.4711. Min Act: -0.1700

Data Index: 1296343 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.4399. Min Act: -0.1700

Data Index: 65199 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.4399. Min Act: -0.1700

Data Index: 1095148 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.4711. Min Act: -0.1700

Data Index: 471581 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.4399. Min Act: -0.1700

Data Index: 941685 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.4399. Min Act: -0.1700

Data Index: 624879 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.5024. Min Act: -0.1700

Data Index: 1194119 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 5.9086. Min Range: -5.9086

Max Act: 5.2836. Min Act: -0.1700

Data Index: 442315 (C4 (Web Text))

Max Activating Token Index: 652