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

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

Neuron 3295 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: 1.7124. Min Range: -1.7124

Max Act: 1.5953. Min Act: -0.0000

Data Index: 699119 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.6977. Min Act: 0.0000

Data Index: 782409 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.7124. Min Act: -0.0000

Data Index: 1237803 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4869. Min Act: -0.0000

Data Index: 815532 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4488. Min Act: -0.0000

Data Index: 1239966 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4840. Min Act: -0.0000

Data Index: 196848 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.6446. Min Act: -0.0000

Data Index: 425076 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4653. Min Act: -0.0000

Data Index: 979080 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.5285. Min Act: -0.0000

Data Index: 607919 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4201. Min Act: -0.0000

Data Index: 828949 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4315. Min Act: -0.0000

Data Index: 409141 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4159. Min Act: -0.0000

Data Index: 1256790 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.4051. Min Act: -0.0000

Data Index: 292044 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.5945. Min Act: 0.0000

Data Index: 661361 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.3305. Min Act: -0.0000

Data Index: 751876 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.3145. Min Act: -0.0000

Data Index: 866177 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.2900. Min Act: -0.0000

Data Index: 639285 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.3487. Min Act: -0.0000

Data Index: 549205 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.3396. Min Act: -0.0000

Data Index: 1603541 (Python Code)

Max Activating Token Index: 849

Text #19

Max Range: 1.7124. Min Range: -1.7124

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1042417 (C4 (Web Text))

Max Activating Token Index: 702