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

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

Neuron 1588 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.4102. Min Act: -0.0001

Data Index: 519786 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3581. Min Act: -0.0001

Data Index: 972118 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3529. Min Act: -0.0001

Data Index: 541156 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.2870. Min Act: -0.0001

Data Index: 824546 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3569. Min Act: -0.0001

Data Index: 1169455 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3272. Min Act: -0.0001

Data Index: 192641 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3443. Min Act: -0.0001

Data Index: 533568 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3277. Min Act: -0.0001

Data Index: 1164165 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3403. Min Act: -0.0001

Data Index: 953463 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1076322 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3287. Min Act: -0.0001

Data Index: 1017328 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3177. Min Act: -0.0001

Data Index: 801648 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3153. Min Act: -0.0001

Data Index: 904267 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3197. Min Act: -0.0001

Data Index: 1255665 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3110. Min Act: -0.0001

Data Index: 377064 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3052. Min Act: -0.0001

Data Index: 615025 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.2942. Min Act: -0.0001

Data Index: 182515 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.2921. Min Act: -0.0001

Data Index: 1044828 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.2976. Min Act: -0.0001

Data Index: 35677 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.4102. Min Range: -0.4102

Max Act: 0.3076. Min Act: -0.0001

Data Index: 7958 (C4 (Web Text))

Max Activating Token Index: 43