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

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

Neuron 1533 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.4114. Min Act: -0.0001

Data Index: 1022015 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3991. Min Act: -0.0000

Data Index: 252657 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1174561 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3793. Min Act: -0.0000

Data Index: 769672 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3765. Min Act: -0.0001

Data Index: 1140395 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3792. Min Act: -0.0000

Data Index: 580531 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3490. Min Act: -0.0001

Data Index: 853387 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1294646 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3532. Min Act: -0.0000

Data Index: 345217 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1236202 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3394. Min Act: -0.0000

Data Index: 624200 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1260927 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1101324 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3290. Min Act: -0.0000

Data Index: 929964 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3393. Min Act: -0.0001

Data Index: 876751 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3368. Min Act: -0.0000

Data Index: 1285940 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1107619 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1320648 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3023. Min Act: -0.0000

Data Index: 417354 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.4114. Min Range: -0.4114

Max Act: 0.3076. Min Act: -0.0001

Data Index: 44344 (C4 (Web Text))

Max Activating Token Index: 1010