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

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

Neuron 1589 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: 0.5668. Min Range: -0.5668

Max Act: 0.5668. Min Act: -0.0001

Data Index: 73079 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.5626. Min Act: -0.0001

Data Index: 1013930 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.5405. Min Act: -0.0001

Data Index: 1262 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4383. Min Act: -0.0001

Data Index: 382009 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4270. Min Act: -0.0001

Data Index: 96079 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3977. Min Act: -0.0001

Data Index: 1310848 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.4146. Min Act: -0.0001

Data Index: 973095 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3828. Min Act: -0.0001

Data Index: 1300804 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3869. Min Act: -0.0001

Data Index: 559783 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3875. Min Act: -0.0001

Data Index: 230530 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3708. Min Act: -0.0001

Data Index: 806819 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3731. Min Act: -0.0001

Data Index: 822766 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3599. Min Act: -0.0001

Data Index: 1155919 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3450. Min Act: -0.0001

Data Index: 682709 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3241. Min Act: -0.0001

Data Index: 775864 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3348. Min Act: -0.0001

Data Index: 765283 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3390. Min Act: -0.0001

Data Index: 1169195 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3174. Min Act: -0.0001

Data Index: 486664 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3341. Min Act: -0.0001

Data Index: 524150 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.5668. Min Range: -0.5668

Max Act: 0.3285. Min Act: -0.0001

Data Index: 506058 (C4 (Web Text))

Max Activating Token Index: 391