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

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

Neuron 521 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: 1.0226. Min Range: -1.0226

Max Act: 1.0226. Min Act: -0.0001

Data Index: 235901 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9571. Min Act: -0.0001

Data Index: 57529 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9336. Min Act: -0.0001

Data Index: 226662 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8986. Min Act: -0.0001

Data Index: 378227 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8590. Min Act: -0.0001

Data Index: 1163384 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8569. Min Act: -0.0001

Data Index: 818913 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.9114. Min Act: -0.0001

Data Index: 1273853 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8501. Min Act: -0.0001

Data Index: 753634 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8794. Min Act: -0.0001

Data Index: 239742 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8000. Min Act: -0.0001

Data Index: 89172 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.7946. Min Act: -0.0001

Data Index: 244478 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8464. Min Act: -0.0001

Data Index: 547283 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8304. Min Act: -0.0001

Data Index: 976500 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8203. Min Act: -0.0001

Data Index: 865635 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8190. Min Act: -0.0001

Data Index: 272415 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.7383. Min Act: -0.0001

Data Index: 814628 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8298. Min Act: -0.0001

Data Index: 484407 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8036. Min Act: -0.0001

Data Index: 1132398 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.8217. Min Act: -0.0001

Data Index: 1300933 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 1.0226. Min Range: -1.0226

Max Act: 0.7670. Min Act: -0.0001

Data Index: 281091 (C4 (Web Text))

Max Activating Token Index: 905