Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1641 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3515. Min Act: -0.0001

Data Index: 754599 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.4070. Min Act: -0.0001

Data Index: 214256 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3754. Min Act: -0.0001

Data Index: 583903 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3514. Min Act: -0.0001

Data Index: 629733 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3455. Min Act: -0.0001

Data Index: 609616 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3524. Min Act: -0.0001

Data Index: 803083 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3237. Min Act: -0.0001

Data Index: 435593 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3299. Min Act: -0.0001

Data Index: 346292 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3238. Min Act: -0.0001

Data Index: 966618 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3198. Min Act: -0.0001

Data Index: 378498 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3276. Min Act: -0.0001

Data Index: 189825 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3269. Min Act: -0.0001

Data Index: 34433 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3105. Min Act: -0.0001

Data Index: 377638 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1210906 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2957. Min Act: -0.0001

Data Index: 1153837 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1173398 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2959. Min Act: -0.0001

Data Index: 907063 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2921. Min Act: -0.0001

Data Index: 853851 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.3089. Min Act: -0.0001

Data Index: 391732 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.4070. Min Range: -0.4070

Max Act: 0.2864. Min Act: -0.0001

Data Index: 871710 (C4 (Web Text))

Max Activating Token Index: 405