Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5054 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.8803. Min Act: -0.0001

Data Index: 924503 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.7139. Min Act: -0.0001

Data Index: 959987 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5986. Min Act: -0.0001

Data Index: 584145 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.7865. Min Act: -0.0001

Data Index: 1154180 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.5036. Min Act: -0.0001

Data Index: 451051 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.3876. Min Act: -0.0001

Data Index: 1201612 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.4435. Min Act: -0.0001

Data Index: 339422 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.4073. Min Act: -0.0001

Data Index: 1255313 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.4023. Min Act: -0.0001

Data Index: 252106 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.2382. Min Act: -0.0001

Data Index: 735212 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.3592. Min Act: -0.0001

Data Index: 1335287 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.3514. Min Act: -0.0001

Data Index: 224135 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.3537. Min Act: -0.0001

Data Index: 820186 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.3218. Min Act: -0.0001

Data Index: 760240 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.1877. Min Act: -0.0001

Data Index: 1314447 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.2207. Min Act: -0.0001

Data Index: 456792 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.2409. Min Act: -0.0001

Data Index: 888898 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.2561. Min Act: -0.0001

Data Index: 1049741 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.2361. Min Act: -0.0001

Data Index: 54327 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 1.8803. Min Range: -1.8803

Max Act: 1.1076. Min Act: -0.0001

Data Index: 341688 (C4 (Web Text))

Max Activating Token Index: 869