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

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

Neuron 5887 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.6134. Min Act: -0.0000

Data Index: 846193 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5367. Min Act: -0.0000

Data Index: 964100 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5997. Min Act: -0.0000

Data Index: 691009 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1415967 (Python Code)

Max Activating Token Index: 916

Text #4

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1102847 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1337203 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1449111 (Python Code)

Max Activating Token Index: 950

Text #7

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1079706 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4929. Min Act: -0.0000

Data Index: 818221 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4599. Min Act: -0.0000

Data Index: 781455 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1121790 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4619. Min Act: -0.0000

Data Index: 941099 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4608. Min Act: -0.0000

Data Index: 339764 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4124. Min Act: -0.0000

Data Index: 447379 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1311842 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4073. Min Act: -0.0000

Data Index: 262990 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4070. Min Act: -0.0000

Data Index: 979761 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1541627 (Python Code)

Max Activating Token Index: 827

Text #18

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1271934 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.6134. Min Range: -0.6134

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1448765 (Python Code)

Max Activating Token Index: 812