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

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

Neuron 1469 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: 1.5089. Min Range: -1.5089

Max Act: 1.5089. Min Act: -0.0001

Data Index: 230332 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.4589. Min Act: -0.0001

Data Index: 699313 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.4196. Min Act: -0.0001

Data Index: 1182260 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1474. Min Act: -0.0001

Data Index: 368223 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.3179. Min Act: -0.0001

Data Index: 330777 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.3076. Min Act: -0.0001

Data Index: 541502 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2450. Min Act: -0.0001

Data Index: 34884 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1558. Min Act: -0.0001

Data Index: 543737 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2841. Min Act: -0.0001

Data Index: 851678 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1760. Min Act: -0.0001

Data Index: 1189136 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1700. Min Act: -0.0001

Data Index: 445952 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2322. Min Act: -0.0001

Data Index: 308758 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.5089. Min Range: -1.5089

Max Act: 0.9931. Min Act: -0.0001

Data Index: 488133 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.2136. Min Act: -0.0001

Data Index: 1227984 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1827. Min Act: -0.0001

Data Index: 1295945 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.3170. Min Act: -0.0001

Data Index: 495567 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1335. Min Act: -0.0001

Data Index: 688263 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1078. Min Act: -0.0001

Data Index: 1270056 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.1349. Min Act: -0.0001

Data Index: 769849 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 1.5089. Min Range: -1.5089

Max Act: 1.0701. Min Act: -0.0001

Data Index: 5768 (C4 (Web Text))

Max Activating Token Index: 564