Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 205 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0442. Min Range: -5.0442

Max Act: 5.0130. Min Act: -0.1700

Data Index: 1285703 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 5.0442. Min Range: -5.0442

Max Act: 5.0442. Min Act: -0.1700

Data Index: 973018 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 5.0442. Min Range: -5.0442

Max Act: 5.0130. Min Act: -0.1700

Data Index: 870425 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.9817. Min Act: -0.1700

Data Index: 640298 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.9817. Min Act: -0.1700

Data Index: 490394 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.9192. Min Act: -0.1700

Data Index: 147881 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.9192. Min Act: -0.1700

Data Index: 403188 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.9192. Min Act: -0.1700

Data Index: 377358 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8880. Min Act: -0.1700

Data Index: 949210 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8567. Min Act: -0.1700

Data Index: 718181 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8255. Min Act: -0.1700

Data Index: 211610 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8255. Min Act: -0.1700

Data Index: 1139505 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8567. Min Act: -0.1700

Data Index: 635392 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8255. Min Act: -0.1700

Data Index: 426220 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.7942. Min Act: -0.1700

Data Index: 823824 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8255. Min Act: -0.1700

Data Index: 141635 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.7942. Min Act: -0.1700

Data Index: 220835 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8567. Min Act: -0.1700

Data Index: 374265 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8255. Min Act: -0.1700

Data Index: 578741 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 5.0442. Min Range: -5.0442

Max Act: 4.8255. Min Act: -0.1700

Data Index: 165626 (C4 (Web Text))

Max Activating Token Index: 315