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

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

Neuron 3856 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.4250. Min Act: -0.0000

Data Index: 602049 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3646. Min Act: -0.0000

Data Index: 139223 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3602. Min Act: -0.0000

Data Index: 698869 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3459. Min Act: 0.0001

Data Index: 1207081 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3455. Min Act: -0.0000

Data Index: 72574 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3356. Min Act: -0.0001

Data Index: 957185 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3226. Min Act: -0.0000

Data Index: 15742 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1004647 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1021002 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3304. Min Act: -0.0000

Data Index: 401110 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3174. Min Act: -0.0000

Data Index: 722486 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3100. Min Act: -0.0000

Data Index: 695122 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3198. Min Act: -0.0000

Data Index: 887809 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3268. Min Act: -0.0000

Data Index: 300457 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3257. Min Act: -0.0000

Data Index: 354324 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1063953 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3156. Min Act: -0.0001

Data Index: 806365 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3100. Min Act: -0.0000

Data Index: 690502 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3103. Min Act: -0.0000

Data Index: 562397 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3020. Min Act: 0.0001

Data Index: 761656 (C4 (Web Text))

Max Activating Token Index: 545