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

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

Neuron 57 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.8898. Min Act: -0.0002

Data Index: 270698 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.6947. Min Act: -0.0001

Data Index: 1151661 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.9236. Min Act: -0.0002

Data Index: 640555 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.6663. Min Act: -0.0001

Data Index: 93803 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.6822. Min Act: -0.0001

Data Index: 331730 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.5764. Min Act: -0.0001

Data Index: 92124 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.5733. Min Act: -0.0002

Data Index: 1089521 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.5884. Min Act: -0.0002

Data Index: 237096 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.5897. Min Act: -0.0002

Data Index: 1059521 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.4569. Min Act: -0.0001

Data Index: 801092 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.5962. Min Act: -0.0002

Data Index: 1051147 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.5929. Min Act: -0.0001

Data Index: 1321163 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.3447. Min Act: -0.0001

Data Index: 1216223 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.5161. Min Act: -0.0002

Data Index: 1082197 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.5073. Min Act: -0.0002

Data Index: 963235 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.6323. Min Act: -0.0001

Data Index: 1080936 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.4532. Min Act: -0.0002

Data Index: 250419 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.3956. Min Act: -0.0002

Data Index: 684610 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.4953. Min Act: -0.0001

Data Index: 1014401 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 1.9236. Min Range: -1.9236

Max Act: 1.5616. Min Act: -0.0002

Data Index: 245906 (C4 (Web Text))

Max Activating Token Index: 215