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

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

Neuron 3037 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4976. Min Act: -0.0001

Data Index: 1103832 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4469. Min Act: -0.0001

Data Index: 1099885 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4253. Min Act: -0.0001

Data Index: 1332936 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4218. Min Act: -0.0001

Data Index: 601228 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4097. Min Act: -0.0001

Data Index: 459770 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.4038. Min Act: -0.0001

Data Index: 684142 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3816. Min Act: -0.0001

Data Index: 343332 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3778. Min Act: -0.0001

Data Index: 992179 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3761. Min Act: -0.0001

Data Index: 882964 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3567. Min Act: -0.0001

Data Index: 763338 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3552. Min Act: -0.0001

Data Index: 468412 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3648. Min Act: -0.0001

Data Index: 636976 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3568. Min Act: -0.0001

Data Index: 180396 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3456. Min Act: -0.0001

Data Index: 694824 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3458. Min Act: -0.0001

Data Index: 999940 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3548. Min Act: -0.0001

Data Index: 429939 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3448. Min Act: -0.0001

Data Index: 1221691 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3412. Min Act: -0.0001

Data Index: 489945 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3346. Min Act: -0.0001

Data Index: 776010 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.4976. Min Range: -0.4976

Max Act: 0.3304. Min Act: -0.0001

Data Index: 506673 (C4 (Web Text))

Max Activating Token Index: 127