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

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

Neuron 5193 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.8656. Min Act: -0.0000

Data Index: 295017 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.8838. Min Act: -0.0001

Data Index: 731217 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.8323. Min Act: -0.0000

Data Index: 337289 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.5162. Min Act: -0.0001

Data Index: 1103311 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.6749. Min Act: -0.0000

Data Index: 1273687 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.5937. Min Act: -0.0001

Data Index: 106161 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4396. Min Act: -0.0000

Data Index: 39085 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.5194. Min Act: -0.0000

Data Index: 1116583 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.6763. Min Act: -0.0001

Data Index: 572658 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4185. Min Act: -0.0000

Data Index: 403472 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4054. Min Act: -0.0001

Data Index: 1048885 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.3230. Min Act: -0.0000

Data Index: 713569 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.2176. Min Act: -0.0000

Data Index: 20068 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4501. Min Act: -0.0000

Data Index: 1127053 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.3279. Min Act: -0.0000

Data Index: 347801 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4913. Min Act: -0.0001

Data Index: 93896 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1006168 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4780. Min Act: -0.0000

Data Index: 743928 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.5845. Min Act: -0.0000

Data Index: 189502 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.8838. Min Range: -1.8838

Max Act: 1.4414. Min Act: -0.0001

Data Index: 255596 (C4 (Web Text))

Max Activating Token Index: 515