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

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

Neuron 3923 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.6190. Min Act: -0.0001

Data Index: 122286 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.6145. Min Act: -0.0001

Data Index: 821137 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5533. Min Act: -0.0001

Data Index: 489509 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5752. Min Act: -0.0001

Data Index: 514980 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5900. Min Act: -0.0001

Data Index: 1289055 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5400. Min Act: -0.0001

Data Index: 251817 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5456. Min Act: -0.0001

Data Index: 914754 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.6019. Min Act: -0.0001

Data Index: 1215073 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5544. Min Act: -0.0001

Data Index: 591604 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5519. Min Act: -0.0001

Data Index: 6539 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5085. Min Act: -0.0001

Data Index: 497529 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5164. Min Act: -0.0001

Data Index: 1011240 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5099. Min Act: -0.0001

Data Index: 665029 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4938. Min Act: -0.0001

Data Index: 978904 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5167. Min Act: -0.0001

Data Index: 562194 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4674. Min Act: -0.0001

Data Index: 435603 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5001. Min Act: -0.0001

Data Index: 661314 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4916. Min Act: -0.0001

Data Index: 19221 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.5053. Min Act: -0.0001

Data Index: 304770 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.6190. Min Range: -0.6190

Max Act: 0.4768. Min Act: -0.0001

Data Index: 1303982 (C4 (Web Text))

Max Activating Token Index: 749