Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 590 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0946. Min Range: -1.0946

Max Act: 1.0946. Min Act: -0.0000

Data Index: 395784 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9844. Min Act: -0.0000

Data Index: 648086 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 1.0946. Min Range: -1.0946

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1133596 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9086. Min Act: -0.0000

Data Index: 793639 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1340624 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8764. Min Act: -0.0000

Data Index: 824311 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1262819 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8699. Min Act: -0.0000

Data Index: 176615 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8403. Min Act: -0.0000

Data Index: 31506 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8084. Min Act: -0.0000

Data Index: 772371 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1236594 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.7243. Min Act: -0.0000

Data Index: 520946 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1350573 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8327. Min Act: -0.0000

Data Index: 295723 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.7376. Min Act: -0.0000

Data Index: 378372 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1076219 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.8081. Min Act: -0.0000

Data Index: 982116 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1061931 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.7079. Min Act: -0.0000

Data Index: 427538 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 1.0946. Min Range: -1.0946

Max Act: 0.6257. Min Act: -0.0000

Data Index: 442960 (C4 (Web Text))

Max Activating Token Index: 888