Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3998 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.8220. Min Act: -0.0001

Data Index: 97012 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.7374. Min Act: -0.0001

Data Index: 793196 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.7379. Min Act: -0.0001

Data Index: 623051 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6902. Min Act: -0.0001

Data Index: 844927 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.7291. Min Act: -0.0001

Data Index: 1340429 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.7231. Min Act: -0.0001

Data Index: 774661 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6945. Min Act: -0.0001

Data Index: 723996 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6617. Min Act: -0.0001

Data Index: 18595 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6800. Min Act: -0.0001

Data Index: 308167 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6688. Min Act: -0.0001

Data Index: 421728 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6871. Min Act: -0.0001

Data Index: 105841 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6328. Min Act: -0.0001

Data Index: 637941 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6475. Min Act: -0.0001

Data Index: 980674 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6398. Min Act: -0.0001

Data Index: 1251122 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6475. Min Act: -0.0001

Data Index: 1345407 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6334. Min Act: -0.0000

Data Index: 585086 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6350. Min Act: -0.0001

Data Index: 623039 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6151. Min Act: -0.0001

Data Index: 903282 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6129. Min Act: -0.0001

Data Index: 216021 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.8220. Min Range: -0.8220

Max Act: 0.6313. Min Act: -0.0001

Data Index: 739685 (C4 (Web Text))

Max Activating Token Index: 469