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

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

Neuron 2771 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4956. Min Act: -0.0001

Data Index: 651894 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4220. Min Act: -0.0001

Data Index: 894232 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4292. Min Act: -0.0000

Data Index: 246636 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3891. Min Act: -0.0000

Data Index: 160287 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3860. Min Act: -0.0000

Data Index: 976942 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3985. Min Act: -0.0000

Data Index: 89309 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3700. Min Act: -0.0001

Data Index: 915968 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3624. Min Act: -0.0000

Data Index: 294329 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3634. Min Act: -0.0001

Data Index: 972834 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3702. Min Act: -0.0001

Data Index: 191287 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3520. Min Act: -0.0000

Data Index: 663279 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3607. Min Act: -0.0000

Data Index: 3296 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3549. Min Act: -0.0001

Data Index: 669004 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3454. Min Act: -0.0000

Data Index: 519530 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3440. Min Act: -0.0000

Data Index: 427306 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3262. Min Act: -0.0001

Data Index: 934621 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3411. Min Act: -0.0000

Data Index: 887122 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3228. Min Act: -0.0000

Data Index: 980473 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3264. Min Act: -0.0000

Data Index: 454448 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3293. Min Act: -0.0001

Data Index: 685616 (C4 (Web Text))

Max Activating Token Index: 578