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

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

Neuron 1425 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: 5.4253. Min Range: -5.4253

Max Act: 5.4253. Min Act: -0.1700

Data Index: 809712 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.4253. Min Act: -0.1700

Data Index: 11196 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.3316. Min Act: -0.1700

Data Index: 21157 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.2691. Min Act: -0.1700

Data Index: 761205 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.2066. Min Act: -0.1700

Data Index: 544971 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.2066. Min Act: -0.1700

Data Index: 954943 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.1441. Min Act: -0.1700

Data Index: 1286583 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.1441. Min Act: -0.1700

Data Index: 811263 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.1441. Min Act: -0.1700

Data Index: 431598 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.1441. Min Act: -0.1700

Data Index: 814728 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.1441. Min Act: -0.1700

Data Index: 1247541 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.1128. Min Act: -0.1700

Data Index: 651568 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.1441. Min Act: -0.1700

Data Index: 490195 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.0816. Min Act: -0.1700

Data Index: 275695 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.1128. Min Act: -0.1700

Data Index: 468586 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.0503. Min Act: -0.1700

Data Index: 969733 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.1128. Min Act: -0.1700

Data Index: 683288 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.0503. Min Act: -0.1700

Data Index: 241284 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.0816. Min Act: -0.1700

Data Index: 932261 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 5.4253. Min Range: -5.4253

Max Act: 5.0503. Min Act: -0.1700

Data Index: 277001 (C4 (Web Text))

Max Activating Token Index: 331