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

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

Neuron 4202 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: 1.6510. Min Range: -1.6510

Max Act: 1.6510. Min Act: -0.0001

Data Index: 1025231 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.4095. Min Act: -0.0001

Data Index: 868974 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.4280. Min Act: -0.0001

Data Index: 895516 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.3366. Min Act: -0.0001

Data Index: 826544 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.2724. Min Act: -0.0001

Data Index: 450130 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.3267. Min Act: -0.0001

Data Index: 441867 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.2730. Min Act: -0.0001

Data Index: 3093 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.0645. Min Act: -0.0001

Data Index: 439339 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.1640. Min Act: -0.0001

Data Index: 554427 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.2203. Min Act: -0.0001

Data Index: 198953 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.2574. Min Act: -0.0001

Data Index: 1131386 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.1249. Min Act: -0.0001

Data Index: 963430 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.1815. Min Act: -0.0001

Data Index: 136157 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.1926. Min Act: -0.0001

Data Index: 214835 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.2530. Min Act: -0.0001

Data Index: 1440014 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.2460. Min Act: -0.0001

Data Index: 946081 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.1712. Min Act: -0.0001

Data Index: 838279 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.1375. Min Act: -0.0001

Data Index: 589185 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.1166. Min Act: -0.0001

Data Index: 265651 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.6510. Min Range: -1.6510

Max Act: 1.1987. Min Act: -0.0001

Data Index: 560471 (C4 (Web Text))

Max Activating Token Index: 812