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

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

Neuron 3935 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.5223. Min Act: -0.0000

Data Index: 832936 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4761. Min Act: -0.0000

Data Index: 758946 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1180286 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4550. Min Act: -0.0001

Data Index: 346046 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4346. Min Act: -0.0000

Data Index: 624161 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4522. Min Act: -0.0001

Data Index: 672082 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4333. Min Act: -0.0001

Data Index: 602608 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1250540 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4035. Min Act: -0.0000

Data Index: 224879 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4245. Min Act: -0.0001

Data Index: 607154 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4200. Min Act: -0.0000

Data Index: 167155 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.4038. Min Act: -0.0000

Data Index: 238003 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.3977. Min Act: -0.0001

Data Index: 467779 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.3943. Min Act: -0.0000

Data Index: 233732 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.3912. Min Act: -0.0001

Data Index: 1076490 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.3779. Min Act: -0.0001

Data Index: 607807 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.3904. Min Act: -0.0001

Data Index: 991947 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.3779. Min Act: -0.0000

Data Index: 515378 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.3808. Min Act: -0.0001

Data Index: 1168998 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.5223. Min Range: -0.5223

Max Act: 0.3769. Min Act: -0.0001

Data Index: 81854 (C4 (Web Text))

Max Activating Token Index: 593