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

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

Neuron 235 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: 3.4407. Min Range: -3.4407

Max Act: 3.4407. Min Act: -0.1700

Data Index: 818837 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.4094. Min Act: -0.1700

Data Index: 91931 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.3623. Min Act: -0.1700

Data Index: 121088 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.3152. Min Act: -0.1700

Data Index: 491735 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.3309. Min Act: -0.1700

Data Index: 77618 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.3152. Min Act: -0.1700

Data Index: 1000160 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.3152. Min Act: -0.1700

Data Index: 1309632 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2681. Min Act: -0.1700

Data Index: 1276018 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2524. Min Act: -0.1700

Data Index: 948597 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2524. Min Act: -0.1700

Data Index: 998879 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2681. Min Act: -0.1700

Data Index: 1248085 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2681. Min Act: -0.1700

Data Index: 647620 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2681. Min Act: -0.1700

Data Index: 833296 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2524. Min Act: -0.1700

Data Index: 919344 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2366. Min Act: -0.1700

Data Index: 617939 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2524. Min Act: -0.1700

Data Index: 249195 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2524. Min Act: -0.1700

Data Index: 905742 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2524. Min Act: -0.1700

Data Index: 1216933 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2524. Min Act: -0.1700

Data Index: 967130 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 3.4407. Min Range: -3.4407

Max Act: 3.2366. Min Act: -0.1700

Data Index: 426289 (C4 (Web Text))

Max Activating Token Index: 615