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

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

Neuron 2320 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.4335. Min Act: -0.0001

Data Index: 400421 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.3646. Min Act: -0.0001

Data Index: 193593 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.3501. Min Act: -0.0001

Data Index: 147733 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.3229. Min Act: -0.0001

Data Index: 209518 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.3112. Min Act: -0.0001

Data Index: 402756 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.3230. Min Act: -0.0001

Data Index: 107191 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1050879 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.3097. Min Act: -0.0001

Data Index: 758741 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2957. Min Act: -0.0001

Data Index: 910644 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2923. Min Act: -0.0001

Data Index: 1189984 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.3038. Min Act: -0.0001

Data Index: 493458 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2994. Min Act: -0.0001

Data Index: 678848 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2944. Min Act: -0.0001

Data Index: 119306 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2835. Min Act: -0.0001

Data Index: 630521 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2738. Min Act: -0.0001

Data Index: 1306783 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2696. Min Act: -0.0001

Data Index: 864025 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2861. Min Act: -0.0001

Data Index: 422101 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2472. Min Act: -0.0001

Data Index: 928798 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2791. Min Act: -0.0001

Data Index: 148266 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.4335. Min Range: -0.4335

Max Act: 0.2565. Min Act: -0.0001

Data Index: 1105180 (C4 (Web Text))

Max Activating Token Index: 842