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

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

Neuron 3483 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.5304. Min Act: -0.0001

Data Index: 310292 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.4977. Min Act: -0.0001

Data Index: 601544 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.5049. Min Act: -0.0001

Data Index: 713316 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.4474. Min Act: -0.0001

Data Index: 692586 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.5258. Min Act: -0.0001

Data Index: 468545 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.4329. Min Act: -0.0001

Data Index: 448800 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.4653. Min Act: -0.0001

Data Index: 163230 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.4166. Min Act: -0.0001

Data Index: 409335 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.4277. Min Act: -0.0001

Data Index: 768626 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.3351. Min Act: -0.0001

Data Index: 691872 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.3545. Min Act: -0.0001

Data Index: 1026386 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.3412. Min Act: -0.0001

Data Index: 953402 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.3052. Min Act: -0.0001

Data Index: 408231 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.3244. Min Act: -0.0001

Data Index: 408091 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.3487. Min Act: -0.0001

Data Index: 241194 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.3153. Min Act: -0.0001

Data Index: 550268 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.3448. Min Act: -0.0001

Data Index: 764777 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.2713. Min Act: -0.0001

Data Index: 444161 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.3046. Min Act: -0.0001

Data Index: 72445 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.5304. Min Range: -1.5304

Max Act: 1.2728. Min Act: -0.0001

Data Index: 994578 (C4 (Web Text))

Max Activating Token Index: 847