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

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

Neuron 3131 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: 0.9318. Min Range: -0.9318

Max Act: 0.8179. Min Act: -0.0000

Data Index: 72938 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.9318. Min Act: -0.0000

Data Index: 682610 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1095749 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7782. Min Act: -0.0000

Data Index: 940760 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7492. Min Act: -0.0000

Data Index: 349224 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7671. Min Act: -0.0000

Data Index: 307283 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7390. Min Act: -0.0000

Data Index: 815051 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.7320. Min Act: -0.0001

Data Index: 803135 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6902. Min Act: -0.0000

Data Index: 505324 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6694. Min Act: -0.0000

Data Index: 141219 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5877. Min Act: -0.0000

Data Index: 640780 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6663. Min Act: -0.0000

Data Index: 498634 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6257. Min Act: -0.0000

Data Index: 647798 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6008. Min Act: -0.0000

Data Index: 69897 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6073. Min Act: -0.0001

Data Index: 61053 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.6019. Min Act: -0.0000

Data Index: 79883 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5567. Min Act: -0.0001

Data Index: 500163 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5773. Min Act: -0.0000

Data Index: 724426 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5566. Min Act: -0.0000

Data Index: 605493 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.9318. Min Range: -0.9318

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1317104 (C4 (Web Text))

Max Activating Token Index: 739