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

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

Neuron 1229 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: 0.8203. Min Range: -0.8203

Max Act: 0.7920. Min Act: -0.0001

Data Index: 726070 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.7793. Min Act: -0.0001

Data Index: 1180064 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.7630. Min Act: -0.0001

Data Index: 430448 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.8203. Min Act: -0.0001

Data Index: 1161169 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.7439. Min Act: -0.0001

Data Index: 1239901 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6855. Min Act: -0.0001

Data Index: 479257 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6901. Min Act: -0.0001

Data Index: 192359 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.7432. Min Act: -0.0001

Data Index: 1327717 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6747. Min Act: -0.0001

Data Index: 292130 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6938. Min Act: -0.0001

Data Index: 232160 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6592. Min Act: -0.0001

Data Index: 674403 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6515. Min Act: -0.0001

Data Index: 158996 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5963. Min Act: -0.0001

Data Index: 768107 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6247. Min Act: -0.0001

Data Index: 1146253 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6478. Min Act: -0.0001

Data Index: 990758 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6194. Min Act: -0.0001

Data Index: 1065645 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6589. Min Act: -0.0001

Data Index: 692011 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6352. Min Act: -0.0001

Data Index: 1230470 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.6342. Min Act: -0.0001

Data Index: 924972 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.8203. Min Range: -0.8203

Max Act: 0.5742. Min Act: -0.0001

Data Index: 1142658 (C4 (Web Text))

Max Activating Token Index: 61