Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1238 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.2448. Min Act: -0.1700

Data Index: 465522 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.1823. Min Act: -0.1700

Data Index: 1344094 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.1823. Min Act: -0.1700

Data Index: 875535 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.1823. Min Act: -0.1700

Data Index: 1234066 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.1823. Min Act: -0.1700

Data Index: 948332 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.1823. Min Act: -0.1700

Data Index: 1086926 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.0886. Min Act: -0.1700

Data Index: 1019100 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.0573. Min Act: -0.1700

Data Index: 1339909 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.0886. Min Act: -0.1700

Data Index: 113198 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.0886. Min Act: -0.1700

Data Index: 1159283 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.0886. Min Act: -0.1700

Data Index: 808928 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.0261. Min Act: -0.1700

Data Index: 422840 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 7.2448. Min Range: -7.2448

Max Act: 6.9948. Min Act: -0.1700

Data Index: 908581 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 7.2448. Min Range: -7.2448

Max Act: 6.9636. Min Act: -0.1700

Data Index: 1071535 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.0261. Min Act: -0.1700

Data Index: 515980 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.0261. Min Act: -0.1700

Data Index: 467736 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 7.2448. Min Range: -7.2448

Max Act: 6.9948. Min Act: -0.1700

Data Index: 761126 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 7.2448. Min Range: -7.2448

Max Act: 7.0261. Min Act: -0.1700

Data Index: 128949 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 7.2448. Min Range: -7.2448

Max Act: 6.9948. Min Act: -0.1700

Data Index: 491696 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 7.2448. Min Range: -7.2448

Max Act: 6.9636. Min Act: -0.1700

Data Index: 280676 (C4 (Web Text))

Max Activating Token Index: 842