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

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

Neuron 3866 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: 0.4033. Min Range: -0.4033

Max Act: 0.4033. Min Act: -0.0000

Data Index: 469277 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.4004. Min Act: -0.0000

Data Index: 229981 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3486. Min Act: -0.0001

Data Index: 149564 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3437. Min Act: -0.0000

Data Index: 980994 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3553. Min Act: -0.0000

Data Index: 86845 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3552. Min Act: -0.0001

Data Index: 92640 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3632. Min Act: -0.0000

Data Index: 771570 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3327. Min Act: -0.0001

Data Index: 120550 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3206. Min Act: -0.0001

Data Index: 950100 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3298. Min Act: -0.0001

Data Index: 442700 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3295. Min Act: -0.0001

Data Index: 663294 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3273. Min Act: -0.0001

Data Index: 980423 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3143. Min Act: -0.0001

Data Index: 1042829 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3034. Min Act: -0.0000

Data Index: 599255 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3121. Min Act: -0.0001

Data Index: 1199234 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1170830 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3198. Min Act: -0.0001

Data Index: 376055 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1325682 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1268209 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.4033. Min Range: -0.4033

Max Act: 0.3063. Min Act: -0.0001

Data Index: 1124990 (C4 (Web Text))

Max Activating Token Index: 648