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

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

Neuron 1589 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: 3.2932. Min Range: -3.2932

Max Act: 3.2932. Min Act: -0.1700

Data Index: 1183347 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.2617. Min Act: -0.1700

Data Index: 1072384 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.2617. Min Act: -0.1700

Data Index: 460147 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.2303. Min Act: -0.1700

Data Index: 1295096 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.2303. Min Act: -0.1700

Data Index: 1124952 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.2146. Min Act: -0.1700

Data Index: 214528 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.2146. Min Act: -0.1700

Data Index: 1290972 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1988. Min Act: -0.1700

Data Index: 975940 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.2146. Min Act: -0.1700

Data Index: 776190 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1831. Min Act: -0.1700

Data Index: 77213 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1831. Min Act: -0.1700

Data Index: 324292 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1831. Min Act: -0.1700

Data Index: 976185 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1988. Min Act: -0.1700

Data Index: 1084593 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1831. Min Act: -0.1700

Data Index: 338789 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1988. Min Act: -0.1700

Data Index: 265902 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1831. Min Act: -0.1700

Data Index: 508112 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1988. Min Act: -0.1700

Data Index: 369190 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1831. Min Act: -0.1700

Data Index: 172725 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1831. Min Act: -0.1700

Data Index: 637205 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.2932. Min Range: -3.2932

Max Act: 3.1831. Min Act: -0.1700

Data Index: 888063 (C4 (Web Text))

Max Activating Token Index: 652