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

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

Neuron 1766 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3505. Min Act: -0.0000

Data Index: 164864 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3414. Min Act: -0.0000

Data Index: 963563 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3364. Min Act: -0.0000

Data Index: 762378 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3351. Min Act: -0.0001

Data Index: 63775 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3286. Min Act: -0.0000

Data Index: 279964 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1199073 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3112. Min Act: -0.0000

Data Index: 355233 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1148747 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3022. Min Act: -0.0000

Data Index: 76318 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3107. Min Act: -0.0000

Data Index: 283052 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1268094 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1332847 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1260141 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3053. Min Act: -0.0000

Data Index: 288476 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2898. Min Act: -0.0000

Data Index: 321016 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1051695 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1151318 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.3000. Min Act: -0.0000

Data Index: 706717 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2904. Min Act: -0.0001

Data Index: 1061241 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.3505. Min Range: -0.3505

Max Act: 0.2966. Min Act: -0.0001

Data Index: 12895 (C4 (Web Text))

Max Activating Token Index: 418