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

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

Neuron 4054 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.4124. Min Act: -0.0001

Data Index: 633364 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3985. Min Act: -0.0001

Data Index: 634131 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.4075. Min Act: -0.0001

Data Index: 712770 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3958. Min Act: -0.0001

Data Index: 46224 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3994. Min Act: -0.0001

Data Index: 1239580 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3847. Min Act: -0.0001

Data Index: 1315660 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.4108. Min Act: -0.0001

Data Index: 644403 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3670. Min Act: -0.0001

Data Index: 1161954 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.4057. Min Act: -0.0001

Data Index: 434836 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3916. Min Act: -0.0001

Data Index: 166986 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.4044. Min Act: -0.0001

Data Index: 1246254 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3780. Min Act: -0.0001

Data Index: 1107987 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.4039. Min Act: -0.0001

Data Index: 1151098 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3641. Min Act: -0.0001

Data Index: 560101 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3980. Min Act: -0.0001

Data Index: 756076 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3976. Min Act: -0.0001

Data Index: 619573 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3727. Min Act: -0.0001

Data Index: 650795 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3835. Min Act: -0.0001

Data Index: 396602 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3820. Min Act: -0.0001

Data Index: 806163 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.4124. Min Range: -0.4124

Max Act: 0.3707. Min Act: -0.0001

Data Index: 445346 (C4 (Web Text))

Max Activating Token Index: 401