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

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

Neuron 915 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.3888. Min Act: -0.1700

Data Index: 1191979 (C4 (Web Text))

Max Activating Token Index: 757

Text #1

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.2013. Min Act: -0.1700

Data Index: 958305 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.1700. Min Act: -0.1700

Data Index: 809983 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.1700. Min Act: -0.1700

Data Index: 287193 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.1700. Min Act: -0.1700

Data Index: 317027 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.1075. Min Act: -0.1700

Data Index: 1196735 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.1388. Min Act: -0.1700

Data Index: 297365 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.1075. Min Act: -0.1700

Data Index: 423723 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.1075. Min Act: -0.1700

Data Index: 511163 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.1075. Min Act: -0.1700

Data Index: 1309675 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.0763. Min Act: -0.1700

Data Index: 395090 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.0450. Min Act: -0.1700

Data Index: 1121387 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.0138. Min Act: -0.1700

Data Index: 505142 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.0450. Min Act: -0.1700

Data Index: 149646 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.1075. Min Act: -0.1700

Data Index: 436299 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.0138. Min Act: -0.1700

Data Index: 506484 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.0138. Min Act: -0.1700

Data Index: 325767 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.0138. Min Act: -0.1700

Data Index: 505329 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 5.3888. Min Range: -5.3888

Max Act: 4.9825. Min Act: -0.1700

Data Index: 869252 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 5.3888. Min Range: -5.3888

Max Act: 5.0138. Min Act: -0.1700

Data Index: 23598 (C4 (Web Text))

Max Activating Token Index: 696