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

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

Neuron 1670 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.8763. Min Act: -0.1700

Data Index: 479001 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.6260. Min Act: -0.1700

Data Index: 835400 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5947. Min Act: -0.1700

Data Index: 937299 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.6103. Min Act: -0.1700

Data Index: 683942 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5947. Min Act: -0.1700

Data Index: 1140407 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5477. Min Act: -0.1700

Data Index: 891247 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5477. Min Act: -0.1700

Data Index: 526918 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5320. Min Act: -0.1700

Data Index: 1277697 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5477. Min Act: -0.1700

Data Index: 1160710 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5164. Min Act: -0.1700

Data Index: 1175274 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5320. Min Act: -0.1700

Data Index: 253719 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5164. Min Act: -0.1700

Data Index: 1302088 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5007. Min Act: -0.1700

Data Index: 409297 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5320. Min Act: -0.1700

Data Index: 439321 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5164. Min Act: -0.1700

Data Index: 1245176 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5164. Min Act: -0.1700

Data Index: 763103 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5164. Min Act: -0.1700

Data Index: 960890 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5164. Min Act: -0.1700

Data Index: 557945 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5007. Min Act: -0.1700

Data Index: 488242 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 3.8763. Min Range: -3.8763

Max Act: 3.5320. Min Act: -0.1700

Data Index: 1098730 (C4 (Web Text))

Max Activating Token Index: 705