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

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

Neuron 765 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: 1.0290. Min Range: -1.0290

Max Act: 1.0036. Min Act: -0.0001

Data Index: 942777 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 1.0290. Min Range: -1.0290

Max Act: 1.0290. Min Act: -0.0001

Data Index: 789021 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8737. Min Act: -0.0001

Data Index: 56584 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8414. Min Act: -0.0001

Data Index: 193804 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8267. Min Act: -0.0001

Data Index: 752507 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8514. Min Act: -0.0000

Data Index: 599117 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7992. Min Act: -0.0000

Data Index: 543826 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1086042 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8414. Min Act: -0.0000

Data Index: 165666 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8967. Min Act: -0.0001

Data Index: 1162090 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8170. Min Act: -0.0001

Data Index: 786401 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8431. Min Act: -0.0001

Data Index: 830902 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8146. Min Act: -0.0000

Data Index: 438830 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8310. Min Act: -0.0001

Data Index: 1309163 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8264. Min Act: -0.0001

Data Index: 887441 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1179196 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7688. Min Act: -0.0000

Data Index: 992786 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8172. Min Act: -0.0001

Data Index: 299309 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.7864. Min Act: -0.0000

Data Index: 994836 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.0290. Min Range: -1.0290

Max Act: 0.8088. Min Act: -0.0001

Data Index: 94066 (C4 (Web Text))

Max Activating Token Index: 903