Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2032 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.9964. Min Act: -0.0000

Data Index: 841739 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.9059. Min Act: -0.0000

Data Index: 220739 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 5.9964. Min Range: -5.9964

Max Act: 5.8020. Min Act: -0.0000

Data Index: 1336778 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.4487. Min Act: -0.0000

Data Index: 1268325 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.3050. Min Act: -0.0000

Data Index: 1102497 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.0775. Min Act: -0.0000

Data Index: 49150 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.2559. Min Act: -0.0000

Data Index: 123267 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.9159. Min Act: -0.0000

Data Index: 313690 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.9225. Min Act: -0.0000

Data Index: 190014 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.9831. Min Act: -0.0000

Data Index: 576383 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.9651. Min Act: -0.0000

Data Index: 290220 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 5.9964. Min Range: -5.9964

Max Act: 4.4325. Min Act: -0.0000

Data Index: 929261 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.5315. Min Act: -0.0000

Data Index: 626902 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.3794. Min Act: -0.0000

Data Index: 192356 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.6630. Min Act: -0.0000

Data Index: 1015170 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.2148. Min Act: -0.0000

Data Index: 1292950 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.3324. Min Act: -0.0000

Data Index: 1247923 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.2754. Min Act: -0.0000

Data Index: 899806 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.2564. Min Act: -0.0000

Data Index: 1116364 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 5.9964. Min Range: -5.9964

Max Act: 3.3924. Min Act: -0.0000

Data Index: 1322572 (C4 (Web Text))

Max Activating Token Index: 674