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

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

Neuron 4540 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.7124. Min Act: -0.0000

Data Index: 531675 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1084076 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1271060 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1161397 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.6012. Min Act: -0.0000

Data Index: 522600 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1145417 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5629. Min Act: -0.0000

Data Index: 829465 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5844. Min Act: -0.0000

Data Index: 498596 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1176957 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1133933 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5507. Min Act: -0.0000

Data Index: 603548 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5365. Min Act: -0.0000

Data Index: 923079 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5386. Min Act: -0.0000

Data Index: 246373 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5244. Min Act: -0.0000

Data Index: 841690 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5568. Min Act: -0.0000

Data Index: 70001 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1273750 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1197816 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5159. Min Act: -0.0000

Data Index: 748895 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5349. Min Act: -0.0000

Data Index: 263675 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.7124. Min Range: -0.7124

Max Act: 0.5202. Min Act: -0.0000

Data Index: 345420 (C4 (Web Text))

Max Activating Token Index: 224