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

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

Neuron 2 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.1397. Min Act: -0.1700

Data Index: 1014901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.1239. Min Act: -0.1700

Data Index: 975538 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0924. Min Act: -0.1700

Data Index: 908106 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0608. Min Act: -0.1700

Data Index: 624986 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0766. Min Act: -0.1700

Data Index: 1121919 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0766. Min Act: -0.1700

Data Index: 615919 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0608. Min Act: -0.1700

Data Index: 1218796 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0450. Min Act: -0.1700

Data Index: 571792 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0293. Min Act: -0.1700

Data Index: 1172925 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0293. Min Act: -0.1700

Data Index: 888730 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0293. Min Act: -0.1700

Data Index: 817027 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0135. Min Act: -0.1700

Data Index: 570261 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0135. Min Act: -0.1700

Data Index: 821452 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0135. Min Act: -0.1700

Data Index: 459402 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 3.1397. Min Range: -3.1397

Max Act: 3.0135. Min Act: -0.1700

Data Index: 316602 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 3.1397. Min Range: -3.1397

Max Act: 2.9818. Min Act: -0.1700

Data Index: 1267607 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 3.1397. Min Range: -3.1397

Max Act: 2.9976. Min Act: -0.1700

Data Index: 796469 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 3.1397. Min Range: -3.1397

Max Act: 2.9976. Min Act: -0.1700

Data Index: 708597 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 3.1397. Min Range: -3.1397

Max Act: 2.9818. Min Act: -0.1700

Data Index: 121970 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 3.1397. Min Range: -3.1397

Max Act: 2.9818. Min Act: -0.1700

Data Index: 665073 (C4 (Web Text))

Max Activating Token Index: 1023