Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1831 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.8064. Min Act: -0.1700

Data Index: 818434 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.7339. Min Act: -0.1700

Data Index: 880992 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.6635. Min Act: -0.1700

Data Index: 938980 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.6542. Min Act: -0.1700

Data Index: 630654 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.6461. Min Act: -0.1700

Data Index: 560166 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.6122. Min Act: -0.1700

Data Index: 1330922 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.6020. Min Act: -0.1700

Data Index: 488350 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5910. Min Act: -0.1700

Data Index: 1460858 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5774. Min Act: -0.1700

Data Index: 515964 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5881. Min Act: -0.1700

Data Index: 528050 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5876. Min Act: -0.1700

Data Index: 414656 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5957. Min Act: -0.1700

Data Index: 265591 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5787. Min Act: -0.1700

Data Index: 195984 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5957. Min Act: -0.1700

Data Index: 79227 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5729. Min Act: -0.1700

Data Index: 196085 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5650. Min Act: -0.1700

Data Index: 653298 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5877. Min Act: -0.1700

Data Index: 126831 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5236. Min Act: -0.1700

Data Index: 748262 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5681. Min Act: -0.1700

Data Index: 616145 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 3.8064. Min Range: -3.8064

Max Act: 3.5489. Min Act: -0.1700

Data Index: 909681 (C4 (Web Text))

Max Activating Token Index: 186