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

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

Neuron 2371 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6109. Min Act: -0.0001

Data Index: 423514 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.6443. Min Act: -0.0002

Data Index: 555544 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5678. Min Act: -0.0001

Data Index: 912256 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5307. Min Act: -0.0001

Data Index: 1084438 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4983. Min Act: -0.0002

Data Index: 495563 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4494. Min Act: -0.0002

Data Index: 921120 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4711. Min Act: -0.0002

Data Index: 468392 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.5014. Min Act: -0.0002

Data Index: 1190541 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4537. Min Act: -0.0002

Data Index: 70498 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4819. Min Act: -0.0002

Data Index: 381641 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4581. Min Act: -0.0001

Data Index: 654017 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4661. Min Act: -0.0001

Data Index: 911153 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4779. Min Act: -0.0002

Data Index: 192581 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4515. Min Act: -0.0001

Data Index: 428792 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4822. Min Act: -0.0002

Data Index: 437730 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4607. Min Act: -0.0001

Data Index: 788656 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4636. Min Act: -0.0002

Data Index: 833038 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4767. Min Act: -0.0001

Data Index: 505475 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4577. Min Act: -0.0001

Data Index: 648964 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.6443. Min Range: -0.6443

Max Act: 0.4694. Min Act: -0.0001

Data Index: 803459 (C4 (Web Text))

Max Activating Token Index: 941