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

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

Neuron 675 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: 1.3862. Min Range: -1.3862

Max Act: 1.3862. Min Act: -0.0001

Data Index: 137911 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.1923. Min Act: -0.0001

Data Index: 1073309 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0416. Min Act: -0.0000

Data Index: 509680 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.3862. Min Range: -1.3862

Max Act: 1.0605. Min Act: -0.0001

Data Index: 695451 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9794. Min Act: -0.0001

Data Index: 1067285 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.9404. Min Act: -0.0001

Data Index: 1187966 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8965. Min Act: -0.0000

Data Index: 18922 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8952. Min Act: -0.0001

Data Index: 1049750 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.7998. Min Act: -0.0001

Data Index: 1227996 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8894. Min Act: -0.0000

Data Index: 325313 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8422. Min Act: -0.0001

Data Index: 570849 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8743. Min Act: -0.0001

Data Index: 945361 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8075. Min Act: -0.0000

Data Index: 259437 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.7987. Min Act: -0.0001

Data Index: 932597 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8359. Min Act: -0.0001

Data Index: 909648 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8058. Min Act: -0.0001

Data Index: 351858 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.7993. Min Act: -0.0001

Data Index: 543335 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8095. Min Act: -0.0001

Data Index: 481619 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8414. Min Act: -0.0000

Data Index: 288243 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 1.3862. Min Range: -1.3862

Max Act: 0.8276. Min Act: -0.0001

Data Index: 646948 (C4 (Web Text))

Max Activating Token Index: 369