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

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

Neuron 1476 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2348. Min Range: -5.2348

Max Act: 5.2348. Min Act: -0.0000

Data Index: 1139675 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.7064. Min Act: -0.0000

Data Index: 190891 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.4305. Min Act: -0.0000

Data Index: 443385 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.4962. Min Act: -0.0000

Data Index: 1447979 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.3428. Min Act: -0.0000

Data Index: 204372 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.3241. Min Act: -0.0000

Data Index: 369020 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.3093. Min Act: -0.0000

Data Index: 1072457 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.2717. Min Act: -0.0000

Data Index: 232095 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.0585. Min Act: -0.0000

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.3385. Min Act: -0.0000

Data Index: 13901 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.1722. Min Act: -0.0000

Data Index: 786315 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.0567. Min Act: -0.0000

Data Index: 958419 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.0643. Min Act: -0.0000

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.0205. Min Act: -0.0000

Data Index: 428371 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 5.2348. Min Range: -5.2348

Max Act: 3.8496. Min Act: -0.0000

Data Index: 79001 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 5.2348. Min Range: -5.2348

Max Act: 4.1389. Min Act: -0.0000

Data Index: 1244025 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 5.2348. Min Range: -5.2348

Max Act: 3.7739. Min Act: -0.0000

Data Index: 1125414 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 5.2348. Min Range: -5.2348

Max Act: 3.7749. Min Act: -0.0000

Data Index: 394697 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 5.2348. Min Range: -5.2348

Max Act: 3.8849. Min Act: -0.0000

Data Index: 351952 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 5.2348. Min Range: -5.2348

Max Act: 3.7487. Min Act: -0.0000

Data Index: 852157 (C4 (Web Text))

Max Activating Token Index: 177