Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1692 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4467. Min Range: -2.4467

Max Act: 2.4467. Min Act: -0.0000

Data Index: 957528 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 2.4467. Min Range: -2.4467

Max Act: 2.2704. Min Act: -0.0000

Data Index: 43027 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.5335. Min Act: -0.0000

Data Index: 151524 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.4854. Min Act: -0.0000

Data Index: 1306041 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.3248. Min Act: -0.0000

Data Index: 860242 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.2988. Min Act: -0.0000

Data Index: 1121742 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.2327. Min Act: -0.0000

Data Index: 792079 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1118189 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1026401 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.1582. Min Act: -0.0000

Data Index: 693178 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.1349. Min Act: -0.0000

Data Index: 1336035 (C4 (Web Text))

Max Activating Token Index: 195

Text #11

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.0408. Min Act: -0.0000

Data Index: 1051985 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.1575. Min Act: -0.0000

Data Index: 438856 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.0429. Min Act: -0.0000

Data Index: 444442 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.0285. Min Act: -0.0000

Data Index: 227088 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.1104. Min Act: -0.0000

Data Index: 927417 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1304255 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.0607. Min Act: -0.0000

Data Index: 299784 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.0200. Min Act: -0.0000

Data Index: 663675 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 2.4467. Min Range: -2.4467

Max Act: 1.1157. Min Act: -0.0000

Data Index: 318419 (C4 (Web Text))

Max Activating Token Index: 821