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

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

Neuron 181 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.5591. Min Act: -0.1700

Data Index: 1161620 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.5121. Min Act: -0.1700

Data Index: 1060095 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.5121. Min Act: -0.1700

Data Index: 621597 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.4024. Min Act: -0.1700

Data Index: 996381 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.4494. Min Act: -0.1700

Data Index: 1187123 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.4651. Min Act: -0.1700

Data Index: 828773 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.4181. Min Act: -0.1700

Data Index: 1006278 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.4024. Min Act: -0.1700

Data Index: 876447 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3553. Min Act: -0.1700

Data Index: 1340201 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3396. Min Act: -0.1700

Data Index: 1118608 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3553. Min Act: -0.1700

Data Index: 106278 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3396. Min Act: -0.1700

Data Index: 189948 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3082. Min Act: -0.1700

Data Index: 309267 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3553. Min Act: -0.1700

Data Index: 1072915 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3396. Min Act: -0.1700

Data Index: 1292083 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3082. Min Act: -0.1700

Data Index: 435955 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3239. Min Act: -0.1700

Data Index: 259640 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3396. Min Act: -0.1700

Data Index: 1219593 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3396. Min Act: -0.1700

Data Index: 1089378 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 3.5591. Min Range: -3.5591

Max Act: 3.3396. Min Act: -0.1700

Data Index: 26706 (C4 (Web Text))

Max Activating Token Index: 105