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

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

Neuron 1414 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: 3.5885. Min Range: -3.5885

Max Act: 3.5885. Min Act: -0.1700

Data Index: 1155545 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4318. Min Act: -0.1700

Data Index: 93720 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4004. Min Act: -0.1700

Data Index: 1094792 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.4004. Min Act: -0.1700

Data Index: 81559 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.3377. Min Act: -0.1700

Data Index: 604559 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.2591. Min Act: -0.1700

Data Index: 813521 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.1490. Min Act: -0.1700

Data Index: 937774 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 3.5885. Min Range: -3.5885

Max Act: 3.1018. Min Act: -0.1700

Data Index: 318771 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.9596. Min Act: -0.1700

Data Index: 747921 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.9121. Min Act: -0.1700

Data Index: 555907 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.9121. Min Act: -0.1700

Data Index: 731111 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.8645. Min Act: -0.1700

Data Index: 760494 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.8168. Min Act: -0.1700

Data Index: 71961 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.8168. Min Act: -0.1700

Data Index: 669878 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.8008. Min Act: -0.1700

Data Index: 1115909 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.8008. Min Act: -0.1700

Data Index: 596264 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.8008. Min Act: -0.1700

Data Index: 103752 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.8008. Min Act: -0.1700

Data Index: 260905 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.8008. Min Act: -0.1700

Data Index: 236205 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 3.5885. Min Range: -3.5885

Max Act: 2.7690. Min Act: -0.1700

Data Index: 760605 (C4 (Web Text))

Max Activating Token Index: 1007