Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 329 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1147. Min Range: -1.1147

Max Act: 1.1147. Min Act: -0.0001

Data Index: 374018 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 1.1147. Min Range: -1.1147

Max Act: 1.0942. Min Act: -0.0001

Data Index: 661603 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.1147. Min Range: -1.1147

Max Act: 1.0545. Min Act: -0.0001

Data Index: 990190 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 1.1147. Min Range: -1.1147

Max Act: 1.0124. Min Act: -0.0001

Data Index: 425346 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 1.1147. Min Range: -1.1147

Max Act: 1.0409. Min Act: -0.0001

Data Index: 367056 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.1147. Min Range: -1.1147

Max Act: 1.0153. Min Act: -0.0001

Data Index: 513685 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9539. Min Act: -0.0001

Data Index: 278515 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.8851. Min Act: -0.0001

Data Index: 1184157 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9252. Min Act: -0.0001

Data Index: 941314 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9494. Min Act: -0.0001

Data Index: 446666 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.1147. Min Range: -1.1147

Max Act: 1.0492. Min Act: -0.0001

Data Index: 1247292 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.8733. Min Act: -0.0001

Data Index: 524332 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9941. Min Act: -0.0001

Data Index: 1103167 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9059. Min Act: -0.0001

Data Index: 793266 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.8678. Min Act: -0.0001

Data Index: 622907 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9239. Min Act: -0.0001

Data Index: 1316533 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9782. Min Act: -0.0001

Data Index: 332201 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9356. Min Act: -0.0001

Data Index: 1298460 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 1.1147. Min Range: -1.1147

Max Act: 0.9215. Min Act: -0.0001

Data Index: 874887 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 1.1147. Min Range: -1.1147

Max Act: 1.0596. Min Act: -0.0001

Data Index: 71567 (C4 (Web Text))

Max Activating Token Index: 537