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

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

Neuron 2473 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7996. Min Act: -0.0001

Data Index: 789959 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.8980. Min Act: -0.0001

Data Index: 1230714 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.8521. Min Act: -0.0001

Data Index: 411845 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.5752. Min Act: -0.0001

Data Index: 662474 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7232. Min Act: -0.0001

Data Index: 373096 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.5049. Min Act: -0.0001

Data Index: 700021 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.6038. Min Act: -0.0001

Data Index: 662199 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.5020. Min Act: -0.0001

Data Index: 846962 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.6647. Min Act: -0.0001

Data Index: 484755 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.5440. Min Act: -0.0001

Data Index: 168847 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.5354. Min Act: -0.0001

Data Index: 153934 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.5216. Min Act: -0.0001

Data Index: 981458 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.3988. Min Act: -0.0001

Data Index: 90284 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.4611. Min Act: -0.0001

Data Index: 1047213 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.5519. Min Act: -0.0001

Data Index: 50945 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.3722. Min Act: -0.0001

Data Index: 1067337 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.3500. Min Act: -0.0001

Data Index: 986353 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1359464 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.3197. Min Act: -0.0001

Data Index: 835761 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.3193. Min Act: -0.0001

Data Index: 1257819 (C4 (Web Text))

Max Activating Token Index: 919